diff options
33 files changed, 447 insertions, 181 deletions
diff --git a/html/footer.html b/html/footer.html index a8f2adf7..bad87ff6 100644 --- a/html/footer.html +++ b/html/footer.html @@ -7,3 +7,7 @@ •
<a href="/" onclick="javascript:gradioApp().getElementById('settings_restart_gradio').click(); return false">Reload UI</a>
</div>
+<br />
+<div class="versions">
+{versions}
+</div>
diff --git a/javascript/hints.js b/javascript/hints.js index 63e17e05..dda66e09 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -81,9 +81,6 @@ titles = { "vram": "Torch active: Peak amount of VRAM used by Torch during generation, excluding cached data.\nTorch reserved: Peak amount of VRAM allocated by Torch, including all active and cached data.\nSys VRAM: Peak amount of VRAM allocation across all applications / total GPU VRAM (peak utilization%).", - "Highres. fix": "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition", - "Scale latent": "Uscale the image in latent space. Alternative is to produce the full image from latent representation, upscale that, and then move it back to latent space.", - "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.", "Do not add watermark to images": "If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be behaving in an unethical manner.", @@ -100,7 +97,13 @@ titles = { "Clip skip": "Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.", "Approx NN": "Cheap neural network approximation. Very fast compared to VAE, but produces pictures with 4 times smaller horizontal/vertical resoluton and lower quality.", - "Approx cheap": "Very cheap approximation. Very fast compared to VAE, but produces pictures with 8 times smaller horizontal/vertical resoluton and extremely low quality." + "Approx cheap": "Very cheap approximation. Very fast compared to VAE, but produces pictures with 8 times smaller horizontal/vertical resoluton and extremely low quality.", + + "Hires. fix": "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition", + "Hires steps": "Number of sampling steps for upscaled picture. If 0, uses same as for original.", + "Upscale by": "Adjusts the size of the image by multiplying the original width and height by the selected value. Ignored if either Resize width to or Resize height to are non-zero.", + "Resize width to": "Resizes image to this width. If 0, width is inferred from either of two nearby sliders.", + "Resize height to": "Resizes image to this height. If 0, height is inferred from either of two nearby sliders." } diff --git a/javascript/imageviewer.js b/javascript/imageviewer.js index 67916536..b7bc2fe1 100644 --- a/javascript/imageviewer.js +++ b/javascript/imageviewer.js @@ -148,8 +148,8 @@ function showGalleryImage() { if(e && e.parentElement.tagName == 'DIV'){ e.style.cursor='pointer' e.style.userSelect='none' - e.addEventListener('click', function (evt) { - if(!opts.js_modal_lightbox) return; + e.addEventListener('mousedown', function (evt) { + if(!opts.js_modal_lightbox || evt.button != 0) return; modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed) showModal(evt) }, true); diff --git a/javascript/ui.js b/javascript/ui.js index 34406f3f..ee226927 100644 --- a/javascript/ui.js +++ b/javascript/ui.js @@ -1,4 +1,4 @@ -// various functions for interation with ui.py not large enough to warrant putting them in separate files +// various functions for interaction with ui.py not large enough to warrant putting them in separate files function set_theme(theme){ gradioURL = window.location.href @@ -13,6 +13,21 @@ dir_extensions = "extensions" python = sys.executable
git = os.environ.get('GIT', "git")
index_url = os.environ.get('INDEX_URL', "")
+stored_commit_hash = None
+
+
+def commit_hash():
+ global stored_commit_hash
+
+ if stored_commit_hash is not None:
+ return stored_commit_hash
+
+ try:
+ stored_commit_hash = run(f"{git} rev-parse HEAD").strip()
+ except Exception:
+ stored_commit_hash = "<none>"
+
+ return stored_commit_hash
def extract_arg(args, name):
@@ -194,10 +209,7 @@ def prepare_environment(): xformers = '--xformers' in sys.argv
ngrok = '--ngrok' in sys.argv
- try:
- commit = run(f"{git} rev-parse HEAD").strip()
- except Exception:
- commit = "<none>"
+ commit = commit_hash()
print(f"Python {sys.version}")
print(f"Commit hash: {commit}")
diff --git a/modules/api/api.py b/modules/api/api.py index 6267afdc..2103709b 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -11,10 +11,10 @@ from fastapi.security import HTTPBasic, HTTPBasicCredentials from secrets import compare_digest import modules.shared as shared -from modules import sd_samplers, deepbooru, sd_hijack +from modules import sd_samplers, deepbooru, sd_hijack, images from modules.api.models import * from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images -from modules.extras import run_extras, run_pnginfo +from modules.extras import run_extras from modules.textual_inversion.textual_inversion import create_embedding, train_embedding from modules.textual_inversion.preprocess import preprocess from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork @@ -101,6 +101,7 @@ class Api: self.router = APIRouter() self.app = app self.queue_lock = queue_lock + api_middleware(self.app) self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=TextToImageResponse) self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=ImageToImageResponse) self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse) @@ -232,9 +233,17 @@ class Api: if(not req.image.strip()): return PNGInfoResponse(info="") - result = run_pnginfo(decode_base64_to_image(req.image.strip())) + image = decode_base64_to_image(req.image.strip()) + if image is None: + return PNGInfoResponse(info="") + + geninfo, items = images.read_info_from_image(image) + if geninfo is None: + geninfo = "" + + items = {**{'parameters': geninfo}, **items} - return PNGInfoResponse(info=result[1]) + return PNGInfoResponse(info=geninfo, items=items) def progressapi(self, req: ProgressRequest = Depends()): # copy from check_progress_call of ui.py diff --git a/modules/api/models.py b/modules/api/models.py index 4a632c68..d8198a27 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -157,7 +157,8 @@ class PNGInfoRequest(BaseModel): image: str = Field(title="Image", description="The base64 encoded PNG image") class PNGInfoResponse(BaseModel): - info: str = Field(title="Image info", description="A string with all the info the image had") + info: str = Field(title="Image info", description="A string with the parameters used to generate the image") + items: dict = Field(title="Items", description="An object containing all the info the image had") class ProgressRequest(BaseModel): skip_current_image: bool = Field(default=False, title="Skip current image", description="Skip current image serialization") @@ -258,4 +259,4 @@ class EmbeddingItem(BaseModel): class EmbeddingsResponse(BaseModel): loaded: Dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model") - skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)")
\ No newline at end of file + skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)") diff --git a/modules/extras.py b/modules/extras.py index d665440a..7407bfe3 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -19,8 +19,6 @@ from modules.shared import opts import modules.gfpgan_model
from modules.ui import plaintext_to_html
import modules.codeformer_model
-import piexif
-import piexif.helper
import gradio as gr
import safetensors.torch
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index 4baf4d9a..12a9de3d 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -212,11 +212,10 @@ def restore_old_hires_fix_params(res): firstpass_width = math.ceil(scale * width / 64) * 64
firstpass_height = math.ceil(scale * height / 64) * 64
- hr_scale = width / firstpass_width if firstpass_width > 0 else height / firstpass_height
-
res['Size-1'] = firstpass_width
res['Size-2'] = firstpass_height
- res['Hires upscale'] = hr_scale
+ res['Hires resize-1'] = width
+ res['Hires resize-2'] = height
def parse_generation_parameters(x: str):
@@ -276,6 +275,10 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model hypernet_hash = res.get("Hypernet hash", None)
res["Hypernet"] = find_hypernetwork_key(hypernet_name, hypernet_hash)
+ if "Hires resize-1" not in res:
+ res["Hires resize-1"] = 0
+ res["Hires resize-2"] = 0
+
restore_old_hires_fix_params(res)
return res
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 450fecac..6a9b1398 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -402,10 +402,8 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, shared.reload_hypernetworks()
- return fn
-
-def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
# images allows training previews to have infotext. Importing it at the top causes a circular import problem.
from modules import images
@@ -448,6 +446,10 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, return hypernetwork, filename
scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
+
+ clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else None
+ if clip_grad:
+ clip_grad_sched = LearnRateScheduler(clip_grad_value, steps, initial_step, verbose=False)
# dataset loading may take a while, so input validations and early returns should be done before this
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
@@ -466,7 +468,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, shared.parallel_processing_allowed = False
shared.sd_model.cond_stage_model.to(devices.cpu)
shared.sd_model.first_stage_model.to(devices.cpu)
-
+
weights = hypernetwork.weights()
hypernetwork.train_mode()
@@ -525,6 +527,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, if shared.state.interrupted:
break
+ if clip_grad:
+ clip_grad_sched.step(hypernetwork.step)
+
with devices.autocast():
x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
if tag_drop_out != 0 or shuffle_tags:
@@ -539,14 +544,14 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, _loss_step += loss.item()
scaler.scale(loss).backward()
+
# go back until we reach gradient accumulation steps
if (j + 1) % gradient_step != 0:
continue
- # print(f"grad:{weights[0].grad.detach().cpu().abs().mean().item():.7f}")
- # scaler.unscale_(optimizer)
- # print(f"grad:{weights[0].grad.detach().cpu().abs().mean().item():.15f}")
- # torch.nn.utils.clip_grad_norm_(weights, max_norm=1.0)
- # print(f"grad:{weights[0].grad.detach().cpu().abs().mean().item():.15f}")
+
+ if clip_grad:
+ clip_grad(weights, clip_grad_sched.learn_rate)
+
scaler.step(optimizer)
scaler.update()
hypernetwork.step += 1
diff --git a/modules/processing.py b/modules/processing.py index fd7c7015..a408d622 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -50,9 +50,9 @@ def apply_color_correction(correction, original_image): correction,
channel_axis=2
), cv2.COLOR_LAB2RGB).astype("uint8"))
-
+
image = blendLayers(image, original_image, BlendType.LUMINOSITY)
-
+
return image
@@ -76,6 +76,24 @@ def apply_overlay(image, paste_loc, index, overlays): return image
+def txt2img_image_conditioning(sd_model, x, width, height):
+ if sd_model.model.conditioning_key not in {'hybrid', 'concat'}:
+ # Dummy zero conditioning if we're not using inpainting model.
+ # Still takes up a bit of memory, but no encoder call.
+ # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
+ return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
+
+ # The "masked-image" in this case will just be all zeros since the entire image is masked.
+ image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
+ image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
+
+ # Add the fake full 1s mask to the first dimension.
+ image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
+ image_conditioning = image_conditioning.to(x.dtype)
+
+ return image_conditioning
+
+
class StableDiffusionProcessing():
"""
The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
@@ -136,28 +154,12 @@ class StableDiffusionProcessing(): self.all_negative_prompts = None
self.all_seeds = None
self.all_subseeds = None
+ self.iteration = 0
def txt2img_image_conditioning(self, x, width=None, height=None):
- if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
- # Dummy zero conditioning if we're not using inpainting model.
- # Still takes up a bit of memory, but no encoder call.
- # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
- return x.new_zeros(x.shape[0], 5, 1, 1)
-
- self.is_using_inpainting_conditioning = True
-
- height = height or self.height
- width = width or self.width
-
- # The "masked-image" in this case will just be all zeros since the entire image is masked.
- image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
- image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning))
-
- # Add the fake full 1s mask to the first dimension.
- image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
- image_conditioning = image_conditioning.to(x.dtype)
+ self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
- return image_conditioning
+ return txt2img_image_conditioning(self.sd_model, x, width or self.width, height or self.height)
def depth2img_image_conditioning(self, source_image):
# Use the AddMiDaS helper to Format our source image to suit the MiDaS model
@@ -420,7 +422,7 @@ def fix_seed(p): p.subseed = get_fixed_seed(p.subseed)
-def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration=0, position_in_batch=0):
+def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0):
index = position_in_batch + iteration * p.batch_size
clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers)
@@ -464,9 +466,15 @@ def process_images(p: StableDiffusionProcessing) -> Processed: try:
for k, v in p.override_settings.items():
setattr(opts, k, v)
- if k == 'sd_hypernetwork': shared.reload_hypernetworks() # make onchange call for changing hypernet
- if k == 'sd_model_checkpoint': sd_models.reload_model_weights() # make onchange call for changing SD model
- if k == 'sd_vae': sd_vae.reload_vae_weights() # make onchange call for changing VAE
+ if k == 'sd_hypernetwork':
+ shared.reload_hypernetworks() # make onchange call for changing hypernet
+
+ if k == 'sd_model_checkpoint':
+ sd_models.reload_model_weights() # make onchange call for changing SD model
+ p.sd_model = shared.sd_model
+
+ if k == 'sd_vae':
+ sd_vae.reload_vae_weights() # make onchange call for changing VAE
res = process_images_inner(p)
@@ -536,6 +544,29 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: infotexts = []
output_images = []
+ cached_uc = [None, None]
+ cached_c = [None, None]
+
+ def get_conds_with_caching(function, required_prompts, steps, cache):
+ """
+ Returns the result of calling function(shared.sd_model, required_prompts, steps)
+ using a cache to store the result if the same arguments have been used before.
+
+ cache is an array containing two elements. The first element is a tuple
+ representing the previously used arguments, or None if no arguments
+ have been used before. The second element is where the previously
+ computed result is stored.
+ """
+
+ if cache[0] is not None and (required_prompts, steps) == cache[0]:
+ return cache[1]
+
+ with devices.autocast():
+ cache[1] = function(shared.sd_model, required_prompts, steps)
+
+ cache[0] = (required_prompts, steps)
+ return cache[1]
+
with torch.no_grad(), p.sd_model.ema_scope():
with devices.autocast():
p.init(p.all_prompts, p.all_seeds, p.all_subseeds)
@@ -544,6 +575,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: state.job_count = p.n_iter
for n in range(p.n_iter):
+ p.iteration = n
+
if state.skipped:
state.skipped = False
@@ -561,9 +594,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.scripts is not None:
p.scripts.process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)
- with devices.autocast():
- uc = prompt_parser.get_learned_conditioning(shared.sd_model, negative_prompts, p.steps)
- c = prompt_parser.get_multicond_learned_conditioning(shared.sd_model, prompts, p.steps)
+ uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc)
+ c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, cached_c)
if len(model_hijack.comments) > 0:
for comment in model_hijack.comments:
@@ -658,12 +690,17 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
sampler = None
- def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, **kwargs):
+ def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, **kwargs):
super().__init__(**kwargs)
self.enable_hr = enable_hr
self.denoising_strength = denoising_strength
self.hr_scale = hr_scale
self.hr_upscaler = hr_upscaler
+ self.hr_second_pass_steps = hr_second_pass_steps
+ self.hr_resize_x = hr_resize_x
+ self.hr_resize_y = hr_resize_y
+ self.hr_upscale_to_x = hr_resize_x
+ self.hr_upscale_to_y = hr_resize_y
if firstphase_width != 0 or firstphase_height != 0:
print("firstphase_width/firstphase_height no longer supported; use hr_scale", file=sys.stderr)
@@ -671,14 +708,60 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.width = firstphase_width
self.height = firstphase_height
+ self.truncate_x = 0
+ self.truncate_y = 0
+
+
def init(self, all_prompts, all_seeds, all_subseeds):
if self.enable_hr:
- if state.job_count == -1:
- state.job_count = self.n_iter * 2
+ if self.hr_resize_x == 0 and self.hr_resize_y == 0:
+ self.extra_generation_params["Hires upscale"] = self.hr_scale
+ self.hr_upscale_to_x = int(self.width * self.hr_scale)
+ self.hr_upscale_to_y = int(self.height * self.hr_scale)
else:
+ self.extra_generation_params["Hires resize"] = f"{self.hr_resize_x}x{self.hr_resize_y}"
+
+ if self.hr_resize_y == 0:
+ self.hr_upscale_to_x = self.hr_resize_x
+ self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
+ elif self.hr_resize_x == 0:
+ self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
+ self.hr_upscale_to_y = self.hr_resize_y
+ else:
+ target_w = self.hr_resize_x
+ target_h = self.hr_resize_y
+ src_ratio = self.width / self.height
+ dst_ratio = self.hr_resize_x / self.hr_resize_y
+
+ if src_ratio < dst_ratio:
+ self.hr_upscale_to_x = self.hr_resize_x
+ self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
+ else:
+ self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
+ self.hr_upscale_to_y = self.hr_resize_y
+
+ self.truncate_x = (self.hr_upscale_to_x - target_w) // opt_f
+ self.truncate_y = (self.hr_upscale_to_y - target_h) // opt_f
+
+ # special case: the user has chosen to do nothing
+ if self.hr_upscale_to_x == self.width and self.hr_upscale_to_y == self.height:
+ self.enable_hr = False
+ self.denoising_strength = None
+ self.extra_generation_params.pop("Hires upscale", None)
+ self.extra_generation_params.pop("Hires resize", None)
+ return
+
+ if not state.processing_has_refined_job_count:
+ if state.job_count == -1:
+ state.job_count = self.n_iter
+
+ shared.total_tqdm.updateTotal((self.steps + (self.hr_second_pass_steps or self.steps)) * state.job_count)
state.job_count = state.job_count * 2
+ state.processing_has_refined_job_count = True
+
+ if self.hr_second_pass_steps:
+ self.extra_generation_params["Hires steps"] = self.hr_second_pass_steps
- self.extra_generation_params["Hires upscale"] = self.hr_scale
if self.hr_upscaler is not None:
self.extra_generation_params["Hires upscaler"] = self.hr_upscaler
@@ -695,8 +778,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if not self.enable_hr:
return samples
- target_width = int(self.width * self.hr_scale)
- target_height = int(self.height * self.hr_scale)
+ target_width = self.hr_upscale_to_x
+ target_height = self.hr_upscale_to_y
def save_intermediate(image, index):
"""saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
@@ -707,7 +790,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if not isinstance(image, Image.Image):
image = sd_samplers.sample_to_image(image, index, approximation=0)
- images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
+ info = create_infotext(self, self.all_prompts, self.all_seeds, self.all_subseeds, [], iteration=self.iteration, position_in_batch=index)
+ images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, info=info, suffix="-before-highres-fix")
if latent_scale_mode is not None:
for i in range(samples.shape[0]):
@@ -750,13 +834,15 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
+ samples = samples[:, :, self.truncate_y//2:samples.shape[2]-(self.truncate_y+1)//2, self.truncate_x//2:samples.shape[3]-(self.truncate_x+1)//2]
+
noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, p=self)
# GC now before running the next img2img to prevent running out of memory
x = None
devices.torch_gc()
- samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps, image_conditioning=image_conditioning)
+ samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
return samples
diff --git a/modules/scripts.py b/modules/scripts.py index 722f8685..0c44f191 100644 --- a/modules/scripts.py +++ b/modules/scripts.py @@ -1,4 +1,5 @@ import os
+import re
import sys
import traceback
from collections import namedtuple
@@ -128,6 +129,15 @@ class Script: """unused"""
return ""
+ def elem_id(self, item_id):
+ """helper function to generate id for a HTML element, constructs final id out of script name, tab and user-supplied item_id"""
+
+ need_tabname = self.show(True) == self.show(False)
+ tabname = ('img2img' if self.is_img2img else 'txt2txt') + "_" if need_tabname else ""
+ title = re.sub(r'[^a-z_0-9]', '', re.sub(r'\s', '_', self.title().lower()))
+
+ return f'script_{tabname}{title}_{item_id}'
+
current_basedir = paths.script_path
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index edcbaf52..fa2cd4bb 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -35,26 +35,35 @@ def apply_optimizations(): ldm.modules.diffusionmodules.model.nonlinearity = silu
ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th
+
+ optimization_method = None
if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):
print("Applying xformers cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
+ optimization_method = 'xformers'
elif cmd_opts.opt_split_attention_v1:
print("Applying v1 cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
+ optimization_method = 'V1'
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention_invokeai or not torch.cuda.is_available()):
if not invokeAI_mps_available and shared.device.type == 'mps':
print("The InvokeAI cross attention optimization for MPS requires the psutil package which is not installed.")
print("Applying v1 cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
+ optimization_method = 'V1'
else:
print("Applying cross attention optimization (InvokeAI).")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_invokeAI
+ optimization_method = 'InvokeAI'
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
print("Applying cross attention optimization (Doggettx).")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
+ optimization_method = 'Doggettx'
+
+ return optimization_method
def undo_optimizations():
@@ -75,6 +84,7 @@ class StableDiffusionModelHijack: layers = None
circular_enabled = False
clip = None
+ optimization_method = None
embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase(cmd_opts.embeddings_dir)
@@ -94,7 +104,7 @@ class StableDiffusionModelHijack: m.cond_stage_model.model.token_embedding = EmbeddingsWithFixes(m.cond_stage_model.model.token_embedding, self)
m.cond_stage_model = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
- apply_optimizations()
+ self.optimization_method = apply_optimizations()
self.clip = m.cond_stage_model
diff --git a/modules/sd_models.py b/modules/sd_models.py index 6dca4ddf..76a89e88 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -171,7 +171,10 @@ def get_state_dict_from_checkpoint(pl_sd): def read_state_dict(checkpoint_file, print_global_state=False, map_location=None):
_, extension = os.path.splitext(checkpoint_file)
if extension.lower() == ".safetensors":
- pl_sd = safetensors.torch.load_file(checkpoint_file, device=map_location or shared.weight_load_location)
+ device = map_location or shared.weight_load_location
+ if device is None:
+ device = devices.get_cuda_device_string() if torch.cuda.is_available() else "cpu"
+ pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
else:
pl_sd = torch.load(checkpoint_file, map_location=map_location or shared.weight_load_location)
@@ -305,9 +308,6 @@ def load_model(checkpoint_info=None): sd_config.model.params.unet_config.params.in_channels = 9
sd_config.model.params.finetune_keys = None
- # Create a "fake" config with a different name so that we know to unload it when switching models.
- checkpoint_info = checkpoint_info._replace(config=checkpoint_config.replace(".yaml", "-inpainting.yaml"))
-
if not hasattr(sd_config.model.params, "use_ema"):
sd_config.model.params.use_ema = False
diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index e904d860..01221b89 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -97,8 +97,9 @@ sampler_extra_params = { def setup_img2img_steps(p, steps=None):
if opts.img2img_fix_steps or steps is not None:
- steps = int((steps or p.steps) / min(p.denoising_strength, 0.999)) if p.denoising_strength > 0 else 0
- t_enc = p.steps - 1
+ requested_steps = (steps or p.steps)
+ steps = int(requested_steps / min(p.denoising_strength, 0.999)) if p.denoising_strength > 0 else 0
+ t_enc = requested_steps - 1
else:
steps = p.steps
t_enc = int(min(p.denoising_strength, 0.999) * steps)
@@ -462,6 +463,13 @@ class KDiffusionSampler: return extra_params_kwargs
def get_sigmas(self, p, steps):
+ discard_next_to_last_sigma = self.config is not None and self.config.options.get('discard_next_to_last_sigma', False)
+ if opts.always_discard_next_to_last_sigma and not discard_next_to_last_sigma:
+ discard_next_to_last_sigma = True
+ p.extra_generation_params["Discard penultimate sigma"] = True
+
+ steps += 1 if discard_next_to_last_sigma else 0
+
if p.sampler_noise_scheduler_override:
sigmas = p.sampler_noise_scheduler_override(steps)
elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
@@ -471,7 +479,7 @@ class KDiffusionSampler: else:
sigmas = self.model_wrap.get_sigmas(steps)
- if self.config is not None and self.config.options.get('discard_next_to_last_sigma', False):
+ if discard_next_to_last_sigma:
sigmas = torch.cat([sigmas[:-2], sigmas[-1:]])
return sigmas
diff --git a/modules/shared.py b/modules/shared.py index 9c9fd857..b7a3ce5c 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -153,6 +153,7 @@ class State: job = ""
job_no = 0
job_count = 0
+ processing_has_refined_job_count = False
job_timestamp = '0'
sampling_step = 0
sampling_steps = 0
@@ -183,6 +184,7 @@ class State: "interrupted": self.interrupted,
"job": self.job,
"job_count": self.job_count,
+ "job_timestamp": self.job_timestamp,
"job_no": self.job_no,
"sampling_step": self.sampling_step,
"sampling_steps": self.sampling_steps,
@@ -193,6 +195,7 @@ class State: def begin(self):
self.sampling_step = 0
self.job_count = -1
+ self.processing_has_refined_job_count = False
self.job_no = 0
self.job_timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
self.current_latent = None
@@ -213,12 +216,13 @@ class State: """sets self.current_image from self.current_latent if enough sampling steps have been made after the last call to this"""
def set_current_image(self):
+ if not parallel_processing_allowed:
+ return
+
if self.sampling_step - self.current_image_sampling_step >= opts.show_progress_every_n_steps and opts.show_progress_every_n_steps > 0:
self.do_set_current_image()
def do_set_current_image(self):
- if not parallel_processing_allowed:
- return
if self.current_latent is None:
return
@@ -230,6 +234,7 @@ class State: self.current_image_sampling_step = self.sampling_step
+
state = State()
artist_db = modules.artists.ArtistsDatabase(os.path.join(script_path, 'artists.csv'))
@@ -437,6 +442,7 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters" 's_tmin': OptionInfo(0.0, "sigma tmin", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}),
+ 'always_discard_next_to_last_sigma': OptionInfo(False, "Always discard next-to-last sigma"),
}))
options_templates.update(options_section((None, "Hidden options"), {
@@ -570,6 +576,7 @@ latent_upscale_modes = { "Latent (bicubic)": {"mode": "bicubic", "antialias": False},
"Latent (bicubic antialiased)": {"mode": "bicubic", "antialias": True},
"Latent (nearest)": {"mode": "nearest", "antialias": False},
+ "Latent (nearest-exact)": {"mode": "nearest-exact", "antialias": False},
}
sd_upscalers = []
@@ -605,7 +612,7 @@ class TotalTQDM: return
if self._tqdm is None:
self.reset()
- self._tqdm.total=new_total
+ self._tqdm.total = new_total
def clear(self):
if self._tqdm is not None:
diff --git a/modules/textual_inversion/learn_schedule.py b/modules/textual_inversion/learn_schedule.py index dd0c0ad1..f63fc72f 100644 --- a/modules/textual_inversion/learn_schedule.py +++ b/modules/textual_inversion/learn_schedule.py @@ -58,14 +58,19 @@ class LearnRateScheduler: self.finished = False
- def apply(self, optimizer, step_number):
+ def step(self, step_number):
if step_number < self.end_step:
- return
+ return False
try:
(self.learn_rate, self.end_step) = next(self.schedules)
- except Exception:
+ except StopIteration:
self.finished = True
+ return False
+ return True
+
+ def apply(self, optimizer, step_number):
+ if not self.step(step_number):
return
if self.verbose:
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 214db01c..24b43045 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -251,7 +251,7 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat if save_model_every or create_image_every:
assert log_directory, "Log directory is empty"
-def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
save_embedding_every = save_embedding_every or 0
create_image_every = create_image_every or 0
validate_train_inputs(embedding_name, learn_rate, batch_size, gradient_step, data_root, template_file, steps, save_embedding_every, create_image_every, log_directory, name="embedding")
@@ -294,6 +294,11 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ return embedding, filename
scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
+ clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else \
+ torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else \
+ None
+ if clip_grad:
+ clip_grad_sched = LearnRateScheduler(clip_grad_value, steps, initial_step, verbose=False)
# dataset loading may take a while, so input validations and early returns should be done before this
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
old_parallel_processing_allowed = shared.parallel_processing_allowed
@@ -325,7 +330,6 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ else:
print("No saved optimizer exists in checkpoint")
-
scaler = torch.cuda.amp.GradScaler()
batch_size = ds.batch_size
@@ -341,6 +345,9 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ forced_filename = "<none>"
embedding_yet_to_be_embedded = False
+ is_training_inpainting_model = shared.sd_model.model.conditioning_key in {'hybrid', 'concat'}
+ img_c = None
+
pbar = tqdm.tqdm(total=steps - initial_step)
try:
for i in range((steps-initial_step) * gradient_step):
@@ -358,14 +365,22 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ if shared.state.interrupted:
break
+ if clip_grad:
+ clip_grad_sched.step(embedding.step)
+
with devices.autocast():
- # c = stack_conds(batch.cond).to(devices.device)
- # mask = torch.tensor(batch.emb_index).to(devices.device, non_blocking=pin_memory)
- # print(mask)
- # c[:, 1:1+embedding.vec.shape[0]] = embedding.vec.to(devices.device, non_blocking=pin_memory)
x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
c = shared.sd_model.cond_stage_model(batch.cond_text)
- loss = shared.sd_model(x, c)[0] / gradient_step
+
+ if is_training_inpainting_model:
+ if img_c is None:
+ img_c = processing.txt2img_image_conditioning(shared.sd_model, c, training_width, training_height)
+
+ cond = {"c_concat": [img_c], "c_crossattn": [c]}
+ else:
+ cond = c
+
+ loss = shared.sd_model(x, cond)[0] / gradient_step
del x
_loss_step += loss.item()
@@ -374,6 +389,10 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ # go back until we reach gradient accumulation steps
if (j + 1) % gradient_step != 0:
continue
+
+ if clip_grad:
+ clip_grad(embedding.vec, clip_grad_sched.learn_rate)
+
scaler.step(optimizer)
scaler.update()
embedding.step += 1
diff --git a/modules/txt2img.py b/modules/txt2img.py index e189a899..38b5f591 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -8,7 +8,7 @@ import modules.processing as processing from modules.ui import plaintext_to_html
-def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, *args):
+def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, *args):
p = StableDiffusionProcessingTxt2Img(
sd_model=shared.sd_model,
outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,
@@ -35,6 +35,9 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: denoising_strength=denoising_strength if enable_hr else None,
hr_scale=hr_scale,
hr_upscaler=hr_upscaler,
+ hr_second_pass_steps=hr_second_pass_steps,
+ hr_resize_x=hr_resize_x,
+ hr_resize_y=hr_resize_y,
)
p.scripts = modules.scripts.scripts_txt2img
diff --git a/modules/ui.py b/modules/ui.py index bfc93634..81d96c5b 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -162,16 +162,14 @@ def save_files(js_data, images, do_make_zip, index): return gr.File.update(value=fullfns, visible=True), plaintext_to_html(f"Saved: {filenames[0]}")
-
-
-def calc_time_left(progress, threshold, label, force_display):
+def calc_time_left(progress, threshold, label, force_display, show_eta):
if progress == 0:
return ""
else:
time_since_start = time.time() - shared.state.time_start
eta = (time_since_start/progress)
eta_relative = eta-time_since_start
- if (eta_relative > threshold and progress > 0.02) or force_display:
+ if (eta_relative > threshold and show_eta) or force_display:
if eta_relative > 3600:
return label + time.strftime('%H:%M:%S', time.gmtime(eta_relative))
elif eta_relative > 60:
@@ -193,7 +191,10 @@ def check_progress_call(id_part): if shared.state.sampling_steps > 0:
progress += 1 / shared.state.job_count * shared.state.sampling_step / shared.state.sampling_steps
- time_left = calc_time_left( progress, 1, " ETA: ", shared.state.time_left_force_display )
+ # Show progress percentage and time left at the same moment, and base it also on steps done
+ show_eta = progress >= 0.01 or shared.state.sampling_step >= 10
+
+ time_left = calc_time_left(progress, 1, " ETA: ", shared.state.time_left_force_display, show_eta)
if time_left != "":
shared.state.time_left_force_display = True
@@ -201,7 +202,7 @@ def check_progress_call(id_part): progressbar = ""
if opts.show_progressbar:
- progressbar = f"""<div class='progressDiv'><div class='progress' style="overflow:visible;width:{progress * 100}%;white-space:nowrap;">{" " * 2 + str(int(progress*100))+"%" + time_left if progress > 0.01 else ""}</div></div>"""
+ progressbar = f"""<div class='progressDiv'><div class='progress' style="overflow:visible;width:{progress * 100}%;white-space:nowrap;">{" " * 2 + str(int(progress*100))+"%" + time_left if show_eta else ""}</div></div>"""
image = gr_show(False)
preview_visibility = gr_show(False)
@@ -559,7 +560,7 @@ Requested path was: {f} generation_info = None
with gr.Column():
with gr.Row(elem_id=f"image_buttons_{tabname}"):
- open_folder_button = gr.Button(folder_symbol, elem_id="hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder')
+ open_folder_button = gr.Button(folder_symbol, elem_id="hidden_element" if shared.cmd_opts.hide_ui_dir_config else f'open_folder_{tabname}')
if tabname != "extras":
save = gr.Button('Save', elem_id=f'save_{tabname}')
@@ -575,13 +576,13 @@ Requested path was: {f} if tabname != "extras":
with gr.Row():
- download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
+ download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False, elem_id=f'download_files_{tabname}')
with gr.Group():
- html_info = gr.HTML()
- html_log = gr.HTML()
+ html_info = gr.HTML(elem_id=f'html_info_{tabname}')
+ html_log = gr.HTML(elem_id=f'html_log_{tabname}')
- generation_info = gr.Textbox(visible=False)
+ generation_info = gr.Textbox(visible=False, elem_id=f'generation_info_{tabname}')
if tabname == 'txt2img' or tabname == 'img2img':
generation_info_button = gr.Button(visible=False, elem_id=f"{tabname}_generation_info_button")
generation_info_button.click(
@@ -623,9 +624,9 @@ Requested path was: {f} )
else:
- html_info_x = gr.HTML()
- html_info = gr.HTML()
- html_log = gr.HTML()
+ html_info_x = gr.HTML(elem_id=f'html_info_x_{tabname}')
+ html_info = gr.HTML(elem_id=f'html_info_{tabname}')
+ html_log = gr.HTML(elem_id=f'html_log_{tabname}')
parameters_copypaste.bind_buttons(buttons, result_gallery, "txt2img" if tabname == "txt2img" else None)
return result_gallery, generation_info if tabname != "extras" else html_info_x, html_info, html_log
@@ -636,10 +637,10 @@ def create_sampler_and_steps_selection(choices, tabname): with FormRow(elem_id=f"sampler_selection_{tabname}"):
sampler_index = gr.Dropdown(label='Sampling method', elem_id=f"{tabname}_sampling", choices=[x.name for x in choices], value=choices[0].name, type="index")
sampler_index.save_to_config = True
- steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling Steps", value=20)
+ steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling steps", value=20)
else:
with FormGroup(elem_id=f"sampler_selection_{tabname}"):
- steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling Steps", value=20)
+ steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling steps", value=20)
sampler_index = gr.Radio(label='Sampling method', elem_id=f"{tabname}_sampling", choices=[x.name for x in choices], value=choices[0].name, type="index")
return steps, sampler_index
@@ -708,10 +709,16 @@ def create_ui(): enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
elif category == "hires_fix":
- with FormRow(visible=False, elem_id="txt2img_hires_fix") as hr_options:
- hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
- hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
- denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
+ with FormGroup(visible=False, elem_id="txt2img_hires_fix") as hr_options:
+ with FormRow(elem_id="txt2img_hires_fix_row1"):
+ hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
+ hr_second_pass_steps = gr.Slider(minimum=0, maximum=150, step=1, label='Hires steps', value=0, elem_id="txt2img_hires_steps")
+ denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
+
+ with FormRow(elem_id="txt2img_hires_fix_row2"):
+ hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
+ hr_resize_x = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize width to", value=0, elem_id="txt2img_hr_resize_x")
+ hr_resize_y = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize height to", value=0, elem_id="txt2img_hr_resize_y")
elif category == "batch":
if not opts.dimensions_and_batch_together:
@@ -752,6 +759,9 @@ def create_ui(): denoising_strength,
hr_scale,
hr_upscaler,
+ hr_second_pass_steps,
+ hr_resize_x,
+ hr_resize_y,
] + custom_inputs,
outputs=[
@@ -803,6 +813,9 @@ def create_ui(): (hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),
(hr_scale, "Hires upscale"),
(hr_upscaler, "Hires upscaler"),
+ (hr_second_pass_steps, "Hires steps"),
+ (hr_resize_x, "Hires resize-1"),
+ (hr_resize_y, "Hires resize-2"),
*modules.scripts.scripts_txt2img.infotext_fields
]
parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields)
@@ -1280,38 +1293,48 @@ def create_ui(): with gr.Tab(label="Train"):
gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images <a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\" style=\"font-weight:bold;\">[wiki]</a></p>")
- with gr.Row():
+ with FormRow():
train_embedding_name = gr.Dropdown(label='Embedding', elem_id="train_embedding", choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
create_refresh_button(train_embedding_name, sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings, lambda: {"choices": sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())}, "refresh_train_embedding_name")
- with gr.Row():
+
train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', elem_id="train_hypernetwork", choices=[x for x in shared.hypernetworks.keys()])
create_refresh_button(train_hypernetwork_name, shared.reload_hypernetworks, lambda: {"choices": sorted([x for x in shared.hypernetworks.keys()])}, "refresh_train_hypernetwork_name")
- with gr.Row():
+
+ with FormRow():
embedding_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005", elem_id="train_embedding_learn_rate")
hypernetwork_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001", elem_id="train_hypernetwork_learn_rate")
+
+ with FormRow():
+ clip_grad_mode = gr.Dropdown(value="disabled", label="Gradient Clipping", choices=["disabled", "value", "norm"])
+ clip_grad_value = gr.Textbox(placeholder="Gradient clip value", value="0.1", show_label=False)
+
+ with FormRow():
+ batch_size = gr.Number(label='Batch size', value=1, precision=0, elem_id="train_batch_size")
+ gradient_step = gr.Number(label='Gradient accumulation steps', value=1, precision=0, elem_id="train_gradient_step")
- batch_size = gr.Number(label='Batch size', value=1, precision=0, elem_id="train_batch_size")
- gradient_step = gr.Number(label='Gradient accumulation steps', value=1, precision=0, elem_id="train_gradient_step")
dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images", elem_id="train_dataset_directory")
log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion", elem_id="train_log_directory")
template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"), elem_id="train_template_file")
training_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="train_training_width")
training_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="train_training_height")
steps = gr.Number(label='Max steps', value=100000, precision=0, elem_id="train_steps")
- create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0, elem_id="train_create_image_every")
- save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0, elem_id="train_save_embedding_every")
+
+ with FormRow():
+ create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0, elem_id="train_create_image_every")
+ save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0, elem_id="train_save_embedding_every")
+
save_image_with_stored_embedding = gr.Checkbox(label='Save images with embedding in PNG chunks', value=True, elem_id="train_save_image_with_stored_embedding")
preview_from_txt2img = gr.Checkbox(label='Read parameters (prompt, etc...) from txt2img tab when making previews', value=False, elem_id="train_preview_from_txt2img")
- with gr.Row():
- shuffle_tags = gr.Checkbox(label="Shuffle tags by ',' when creating prompts.", value=False, elem_id="train_shuffle_tags")
- tag_drop_out = gr.Slider(minimum=0, maximum=1, step=0.1, label="Drop out tags when creating prompts.", value=0, elem_id="train_tag_drop_out")
- with gr.Row():
- latent_sampling_method = gr.Radio(label='Choose latent sampling method', value="once", choices=['once', 'deterministic', 'random'], elem_id="train_latent_sampling_method")
+
+ shuffle_tags = gr.Checkbox(label="Shuffle tags by ',' when creating prompts.", value=False, elem_id="train_shuffle_tags")
+ tag_drop_out = gr.Slider(minimum=0, maximum=1, step=0.1, label="Drop out tags when creating prompts.", value=0, elem_id="train_tag_drop_out")
+
+ latent_sampling_method = gr.Radio(label='Choose latent sampling method', value="once", choices=['once', 'deterministic', 'random'], elem_id="train_latent_sampling_method")
with gr.Row():
+ train_embedding = gr.Button(value="Train Embedding", variant='primary', elem_id="train_train_embedding")
interrupt_training = gr.Button(value="Interrupt", elem_id="train_interrupt_training")
train_hypernetwork = gr.Button(value="Train Hypernetwork", variant='primary', elem_id="train_train_hypernetwork")
- train_embedding = gr.Button(value="Train Embedding", variant='primary', elem_id="train_train_embedding")
params = script_callbacks.UiTrainTabParams(txt2img_preview_params)
@@ -1401,6 +1424,8 @@ def create_ui(): training_width,
training_height,
steps,
+ clip_grad_mode,
+ clip_grad_value,
shuffle_tags,
tag_drop_out,
latent_sampling_method,
@@ -1430,6 +1455,8 @@ def create_ui(): training_width,
training_height,
steps,
+ clip_grad_mode,
+ clip_grad_value,
shuffle_tags,
tag_drop_out,
latent_sampling_method,
@@ -1669,7 +1696,9 @@ def create_ui(): if os.path.exists("html/footer.html"):
with open("html/footer.html", encoding="utf8") as file:
- gr.HTML(file.read(), elem_id="footer")
+ footer = file.read()
+ footer = footer.format(versions=versions_html())
+ gr.HTML(footer, elem_id="footer")
text_settings = gr.Textbox(elem_id="settings_json", value=lambda: opts.dumpjson(), visible=False)
settings_submit.click(
@@ -1794,6 +1823,7 @@ def create_ui(): visit(img2img_interface, loadsave, "img2img")
visit(extras_interface, loadsave, "extras")
visit(modelmerger_interface, loadsave, "modelmerger")
+ visit(train_interface, loadsave, "train")
if not error_loading and (not os.path.exists(ui_config_file) or settings_count != len(ui_settings)):
with open(ui_config_file, "w", encoding="utf8") as file:
@@ -1829,3 +1859,30 @@ def reload_javascript(): if not hasattr(shared, 'GradioTemplateResponseOriginal'):
shared.GradioTemplateResponseOriginal = gradio.routes.templates.TemplateResponse
+
+
+def versions_html():
+ import torch
+ import launch
+
+ python_version = ".".join([str(x) for x in sys.version_info[0:3]])
+ commit = launch.commit_hash()
+ short_commit = commit[0:8]
+
+ if shared.xformers_available:
+ import xformers
+ xformers_version = xformers.__version__
+ else:
+ xformers_version = "N/A"
+
+ return f"""
+python: <span title="{sys.version}">{python_version}</span>
+ •
+torch: {torch.__version__}
+ •
+xformers: {xformers_version}
+ •
+gradio: {gr.__version__}
+ •
+commit: <a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/{commit}">{short_commit}</a>
+"""
diff --git a/requirements_versions.txt b/requirements_versions.txt index 836523ba..d2899292 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -5,7 +5,7 @@ basicsr==1.4.2 gfpgan==1.3.8
gradio==3.15.0
numpy==1.23.3
-Pillow==9.2.0
+Pillow==9.4.0
realesrgan==0.3.0
torch
omegaconf==2.2.3
@@ -26,5 +26,5 @@ lark==1.1.2 inflection==0.5.1
GitPython==3.1.27
torchsde==0.2.5
-safetensors==0.2.5
+safetensors==0.2.7
httpcore<=0.15
diff --git a/scripts/custom_code.py b/scripts/custom_code.py index 22e7b77a..d29113e6 100644 --- a/scripts/custom_code.py +++ b/scripts/custom_code.py @@ -9,12 +9,11 @@ class Script(scripts.Script): def title(self):
return "Custom code"
-
def show(self, is_img2img):
return cmd_opts.allow_code
def ui(self, is_img2img):
- code = gr.Textbox(label="Python code", lines=1)
+ code = gr.Textbox(label="Python code", lines=1, elem_id=self.elem_id("code"))
return [code]
diff --git a/scripts/img2imgalt.py b/scripts/img2imgalt.py index 1229f61b..cbdfc6b3 100644 --- a/scripts/img2imgalt.py +++ b/scripts/img2imgalt.py @@ -125,25 +125,25 @@ class Script(scripts.Script): def show(self, is_img2img):
return is_img2img
- def ui(self, is_img2img):
+ def ui(self, is_img2img):
info = gr.Markdown('''
* `CFG Scale` should be 2 or lower.
''')
- override_sampler = gr.Checkbox(label="Override `Sampling method` to Euler?(this method is built for it)", value=True)
+ override_sampler = gr.Checkbox(label="Override `Sampling method` to Euler?(this method is built for it)", value=True, elem_id=self.elem_id("override_sampler"))
- override_prompt = gr.Checkbox(label="Override `prompt` to the same value as `original prompt`?(and `negative prompt`)", value=True)
- original_prompt = gr.Textbox(label="Original prompt", lines=1)
- original_negative_prompt = gr.Textbox(label="Original negative prompt", lines=1)
+ override_prompt = gr.Checkbox(label="Override `prompt` to the same value as `original prompt`?(and `negative prompt`)", value=True, elem_id=self.elem_id("override_prompt"))
+ original_prompt = gr.Textbox(label="Original prompt", lines=1, elem_id=self.elem_id("original_prompt"))
+ original_negative_prompt = gr.Textbox(label="Original negative prompt", lines=1, elem_id=self.elem_id("original_negative_prompt"))
- override_steps = gr.Checkbox(label="Override `Sampling Steps` to the same value as `Decode steps`?", value=True)
- st = gr.Slider(label="Decode steps", minimum=1, maximum=150, step=1, value=50)
+ override_steps = gr.Checkbox(label="Override `Sampling Steps` to the same value as `Decode steps`?", value=True, elem_id=self.elem_id("override_steps"))
+ st = gr.Slider(label="Decode steps", minimum=1, maximum=150, step=1, value=50, elem_id=self.elem_id("st"))
- override_strength = gr.Checkbox(label="Override `Denoising strength` to 1?", value=True)
+ override_strength = gr.Checkbox(label="Override `Denoising strength` to 1?", value=True, elem_id=self.elem_id("override_strength"))
- cfg = gr.Slider(label="Decode CFG scale", minimum=0.0, maximum=15.0, step=0.1, value=1.0)
- randomness = gr.Slider(label="Randomness", minimum=0.0, maximum=1.0, step=0.01, value=0.0)
- sigma_adjustment = gr.Checkbox(label="Sigma adjustment for finding noise for image", value=False)
+ cfg = gr.Slider(label="Decode CFG scale", minimum=0.0, maximum=15.0, step=0.1, value=1.0, elem_id=self.elem_id("cfg"))
+ randomness = gr.Slider(label="Randomness", minimum=0.0, maximum=1.0, step=0.01, value=0.0, elem_id=self.elem_id("randomness"))
+ sigma_adjustment = gr.Checkbox(label="Sigma adjustment for finding noise for image", value=False, elem_id=self.elem_id("sigma_adjustment"))
return [
info,
diff --git a/scripts/loopback.py b/scripts/loopback.py index d8c68af8..1dab9476 100644 --- a/scripts/loopback.py +++ b/scripts/loopback.py @@ -9,6 +9,7 @@ from modules.processing import Processed from modules.sd_samplers import samplers
from modules.shared import opts, cmd_opts, state
+
class Script(scripts.Script):
def title(self):
return "Loopback"
@@ -16,9 +17,9 @@ class Script(scripts.Script): def show(self, is_img2img):
return is_img2img
- def ui(self, is_img2img):
- loops = gr.Slider(minimum=1, maximum=32, step=1, label='Loops', value=4)
- denoising_strength_change_factor = gr.Slider(minimum=0.9, maximum=1.1, step=0.01, label='Denoising strength change factor', value=1)
+ def ui(self, is_img2img):
+ loops = gr.Slider(minimum=1, maximum=32, step=1, label='Loops', value=4, elem_id=self.elem_id("loops"))
+ denoising_strength_change_factor = gr.Slider(minimum=0.9, maximum=1.1, step=0.01, label='Denoising strength change factor', value=1, elem_id=self.elem_id("denoising_strength_change_factor"))
return [loops, denoising_strength_change_factor]
diff --git a/scripts/outpainting_mk_2.py b/scripts/outpainting_mk_2.py index cf71cb92..0906da6a 100644 --- a/scripts/outpainting_mk_2.py +++ b/scripts/outpainting_mk_2.py @@ -131,11 +131,11 @@ class Script(scripts.Script): info = gr.HTML("<p style=\"margin-bottom:0.75em\">Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8</p>")
- pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128)
- mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=8)
- direction = gr.CheckboxGroup(label="Outpainting direction", choices=['left', 'right', 'up', 'down'], value=['left', 'right', 'up', 'down'])
- noise_q = gr.Slider(label="Fall-off exponent (lower=higher detail)", minimum=0.0, maximum=4.0, step=0.01, value=1.0)
- color_variation = gr.Slider(label="Color variation", minimum=0.0, maximum=1.0, step=0.01, value=0.05)
+ pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128, elem_id=self.elem_id("pixels"))
+ mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=8, elem_id=self.elem_id("mask_blur"))
+ direction = gr.CheckboxGroup(label="Outpainting direction", choices=['left', 'right', 'up', 'down'], value=['left', 'right', 'up', 'down'], elem_id=self.elem_id("direction"))
+ noise_q = gr.Slider(label="Fall-off exponent (lower=higher detail)", minimum=0.0, maximum=4.0, step=0.01, value=1.0, elem_id=self.elem_id("noise_q"))
+ color_variation = gr.Slider(label="Color variation", minimum=0.0, maximum=1.0, step=0.01, value=0.05, elem_id=self.elem_id("color_variation"))
return [info, pixels, mask_blur, direction, noise_q, color_variation]
diff --git a/scripts/poor_mans_outpainting.py b/scripts/poor_mans_outpainting.py index ea45beb0..d8feda00 100644 --- a/scripts/poor_mans_outpainting.py +++ b/scripts/poor_mans_outpainting.py @@ -9,7 +9,6 @@ from modules.processing import Processed, process_images from modules.shared import opts, cmd_opts, state
-
class Script(scripts.Script):
def title(self):
return "Poor man's outpainting"
@@ -20,11 +19,11 @@ class Script(scripts.Script): def ui(self, is_img2img):
if not is_img2img:
return None
-
- pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128)
- mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4)
- inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='fill', type="index")
- direction = gr.CheckboxGroup(label="Outpainting direction", choices=['left', 'right', 'up', 'down'], value=['left', 'right', 'up', 'down'])
+
+ pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128, elem_id=self.elem_id("pixels"))
+ mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4, elem_id=self.elem_id("mask_blur"))
+ inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='fill', type="index", elem_id=self.elem_id("inpainting_fill"))
+ direction = gr.CheckboxGroup(label="Outpainting direction", choices=['left', 'right', 'up', 'down'], value=['left', 'right', 'up', 'down'], elem_id=self.elem_id("direction"))
return [pixels, mask_blur, inpainting_fill, direction]
diff --git a/scripts/prompt_matrix.py b/scripts/prompt_matrix.py index 4c79eaef..dd95e588 100644 --- a/scripts/prompt_matrix.py +++ b/scripts/prompt_matrix.py @@ -44,9 +44,9 @@ class Script(scripts.Script): def title(self):
return "Prompt matrix"
- def ui(self, is_img2img):
- put_at_start = gr.Checkbox(label='Put variable parts at start of prompt', value=False)
- different_seeds = gr.Checkbox(label='Use different seed for each picture', value=False)
+ def ui(self, is_img2img):
+ put_at_start = gr.Checkbox(label='Put variable parts at start of prompt', value=False, elem_id=self.elem_id("put_at_start"))
+ different_seeds = gr.Checkbox(label='Use different seed for each picture', value=False, elem_id=self.elem_id("different_seeds"))
return [put_at_start, different_seeds]
diff --git a/scripts/prompts_from_file.py b/scripts/prompts_from_file.py index e8386ed2..2751f98a 100644 --- a/scripts/prompts_from_file.py +++ b/scripts/prompts_from_file.py @@ -111,12 +111,12 @@ class Script(scripts.Script): def title(self):
return "Prompts from file or textbox"
- def ui(self, is_img2img):
- checkbox_iterate = gr.Checkbox(label="Iterate seed every line", value=False)
- checkbox_iterate_batch = gr.Checkbox(label="Use same random seed for all lines", value=False)
+ def ui(self, is_img2img):
+ checkbox_iterate = gr.Checkbox(label="Iterate seed every line", value=False, elem_id=self.elem_id("checkbox_iterate"))
+ checkbox_iterate_batch = gr.Checkbox(label="Use same random seed for all lines", value=False, elem_id=self.elem_id("checkbox_iterate_batch"))
- prompt_txt = gr.Textbox(label="List of prompt inputs", lines=1)
- file = gr.File(label="Upload prompt inputs", type='bytes')
+ prompt_txt = gr.Textbox(label="List of prompt inputs", lines=1, elem_id=self.elem_id("prompt_txt"))
+ file = gr.File(label="Upload prompt inputs", type='bytes', elem_id=self.elem_id("file"))
file.change(fn=load_prompt_file, inputs=[file], outputs=[file, prompt_txt, prompt_txt])
diff --git a/scripts/sd_upscale.py b/scripts/sd_upscale.py index 9739545c..9b8ffd85 100644 --- a/scripts/sd_upscale.py +++ b/scripts/sd_upscale.py @@ -16,11 +16,11 @@ class Script(scripts.Script): def show(self, is_img2img):
return is_img2img
- def ui(self, is_img2img):
+ def ui(self, is_img2img):
info = gr.HTML("<p style=\"margin-bottom:0.75em\">Will upscale the image by the selected scale factor; use width and height sliders to set tile size</p>")
- overlap = gr.Slider(minimum=0, maximum=256, step=16, label='Tile overlap', value=64)
- scale_factor = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label='Scale Factor', value=2.0)
- upscaler_index = gr.Radio(label='Upscaler', choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name, type="index")
+ overlap = gr.Slider(minimum=0, maximum=256, step=16, label='Tile overlap', value=64, elem_id=self.elem_id("overlap"))
+ scale_factor = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label='Scale Factor', value=2.0, elem_id=self.elem_id("scale_factor"))
+ upscaler_index = gr.Radio(label='Upscaler', choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name, type="index", elem_id=self.elem_id("upscaler_index"))
return [info, overlap, upscaler_index, scale_factor]
diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index f92f9776..f04d9b7e 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -10,7 +10,7 @@ import numpy as np import modules.scripts as scripts
import gradio as gr
-from modules import images, paths, sd_samplers
+from modules import images, paths, sd_samplers, processing
from modules.hypernetworks import hypernetwork
from modules.processing import process_images, Processed, StableDiffusionProcessingTxt2Img
from modules.shared import opts, cmd_opts, state
@@ -285,6 +285,7 @@ re_range_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d re_range_count = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\[(\d+)\s*\])?\s*")
re_range_count_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d*)?)(?:\s*\[(\d+(?:.\d*)?)\s*\])?\s*")
+
class Script(scripts.Script):
def title(self):
return "X/Y plot"
@@ -293,16 +294,16 @@ class Script(scripts.Script): current_axis_options = [x for x in axis_options if type(x) == AxisOption or type(x) == AxisOptionImg2Img and is_img2img]
with gr.Row():
- x_type = gr.Dropdown(label="X type", choices=[x.label for x in current_axis_options], value=current_axis_options[1].label, type="index", elem_id="x_type")
- x_values = gr.Textbox(label="X values", lines=1)
+ x_type = gr.Dropdown(label="X type", choices=[x.label for x in current_axis_options], value=current_axis_options[1].label, type="index", elem_id=self.elem_id("x_type"))
+ x_values = gr.Textbox(label="X values", lines=1, elem_id=self.elem_id("x_values"))
with gr.Row():
- y_type = gr.Dropdown(label="Y type", choices=[x.label for x in current_axis_options], value=current_axis_options[0].label, type="index", elem_id="y_type")
- y_values = gr.Textbox(label="Y values", lines=1)
+ y_type = gr.Dropdown(label="Y type", choices=[x.label for x in current_axis_options], value=current_axis_options[0].label, type="index", elem_id=self.elem_id("y_type"))
+ y_values = gr.Textbox(label="Y values", lines=1, elem_id=self.elem_id("y_values"))
- draw_legend = gr.Checkbox(label='Draw legend', value=True)
- include_lone_images = gr.Checkbox(label='Include Separate Images', value=False)
- no_fixed_seeds = gr.Checkbox(label='Keep -1 for seeds', value=False)
+ draw_legend = gr.Checkbox(label='Draw legend', value=True, elem_id=self.elem_id("draw_legend"))
+ include_lone_images = gr.Checkbox(label='Include Separate Images', value=False, elem_id=self.elem_id("include_lone_images"))
+ no_fixed_seeds = gr.Checkbox(label='Keep -1 for seeds', value=False, elem_id=self.elem_id("no_fixed_seeds"))
return [x_type, x_values, y_type, y_values, draw_legend, include_lone_images, no_fixed_seeds]
@@ -381,7 +382,7 @@ class Script(scripts.Script): ys = process_axis(y_opt, y_values)
def fix_axis_seeds(axis_opt, axis_list):
- if axis_opt.label in ['Seed','Var. seed']:
+ if axis_opt.label in ['Seed', 'Var. seed']:
return [int(random.randrange(4294967294)) if val is None or val == '' or val == -1 else val for val in axis_list]
else:
return axis_list
@@ -403,12 +404,33 @@ class Script(scripts.Script): print(f"X/Y plot will create {len(xs) * len(ys) * p.n_iter} images on a {len(xs)}x{len(ys)} grid. (Total steps to process: {total_steps * p.n_iter})")
shared.total_tqdm.updateTotal(total_steps * p.n_iter)
+ grid_infotext = [None]
+
def cell(x, y):
pc = copy(p)
x_opt.apply(pc, x, xs)
y_opt.apply(pc, y, ys)
- return process_images(pc)
+ res = process_images(pc)
+
+ if grid_infotext[0] is None:
+ pc.extra_generation_params = copy(pc.extra_generation_params)
+
+ if x_opt.label != 'Nothing':
+ pc.extra_generation_params["X Type"] = x_opt.label
+ pc.extra_generation_params["X Values"] = x_values
+ if x_opt.label in ["Seed", "Var. seed"] and not no_fixed_seeds:
+ pc.extra_generation_params["Fixed X Values"] = ", ".join([str(x) for x in xs])
+
+ if y_opt.label != 'Nothing':
+ pc.extra_generation_params["Y Type"] = y_opt.label
+ pc.extra_generation_params["Y Values"] = y_values
+ if y_opt.label in ["Seed", "Var. seed"] and not no_fixed_seeds:
+ pc.extra_generation_params["Fixed Y Values"] = ", ".join([str(y) for y in ys])
+
+ grid_infotext[0] = processing.create_infotext(pc, pc.all_prompts, pc.all_seeds, pc.all_subseeds)
+
+ return res
with SharedSettingsStackHelper():
processed = draw_xy_grid(
@@ -423,6 +445,6 @@ class Script(scripts.Script): )
if opts.grid_save:
- images.save_image(processed.images[0], p.outpath_grids, "xy_grid", extension=opts.grid_format, prompt=p.prompt, seed=processed.seed, grid=True, p=p)
+ images.save_image(processed.images[0], p.outpath_grids, "xy_grid", info=grid_infotext[0], extension=opts.grid_format, prompt=p.prompt, seed=processed.seed, grid=True, p=p)
return processed
@@ -611,7 +611,7 @@ img2maskimg, #img2maskimg > .h-60, #img2maskimg > .h-60 > div, #img2maskimg > .h padding-top: 0.9em;
}
-#img2img_settings div.gr-form .gr-form, #txt2img_settings div.gr-form .gr-form{
+#img2img_settings div.gr-form .gr-form, #txt2img_settings div.gr-form .gr-form, #train_tabs div.gr-form .gr-form{
border: none;
padding-bottom: 0.5em;
}
@@ -628,6 +628,11 @@ footer { display: inline-block;
}
+#footer .versions{
+ font-size: 85%;
+ opacity: 0.85;
+}
+
/* The following handles localization for right-to-left (RTL) languages like Arabic.
The rtl media type will only be activated by the logic in javascript/localization.js.
If you change anything above, you need to make sure it is RTL compliant by just running
@@ -105,11 +105,11 @@ def initialize(): def setup_cors(app):
if cmd_opts.cors_allow_origins and cmd_opts.cors_allow_origins_regex:
- app.add_middleware(CORSMiddleware, allow_origins=cmd_opts.cors_allow_origins.split(','), allow_origin_regex=cmd_opts.cors_allow_origins_regex, allow_methods=['*'])
+ app.add_middleware(CORSMiddleware, allow_origins=cmd_opts.cors_allow_origins.split(','), allow_origin_regex=cmd_opts.cors_allow_origins_regex, allow_methods=['*'], allow_credentials=True, allow_headers=['*'])
elif cmd_opts.cors_allow_origins:
- app.add_middleware(CORSMiddleware, allow_origins=cmd_opts.cors_allow_origins.split(','), allow_methods=['*'])
+ app.add_middleware(CORSMiddleware, allow_origins=cmd_opts.cors_allow_origins.split(','), allow_methods=['*'], allow_credentials=True, allow_headers=['*'])
elif cmd_opts.cors_allow_origins_regex:
- app.add_middleware(CORSMiddleware, allow_origin_regex=cmd_opts.cors_allow_origins_regex, allow_methods=['*'])
+ app.add_middleware(CORSMiddleware, allow_origin_regex=cmd_opts.cors_allow_origins_regex, allow_methods=['*'], allow_credentials=True, allow_headers=['*'])
def create_api(app):
@@ -160,10 +160,10 @@ then printf "\n%s\n" "${delimiter}" printf "Accelerating launch.py..." printf "\n%s\n" "${delimiter}" - accelerate launch --num_cpu_threads_per_process=6 "${LAUNCH_SCRIPT}" "$@" + exec accelerate launch --num_cpu_threads_per_process=6 "${LAUNCH_SCRIPT}" "$@" else printf "\n%s\n" "${delimiter}" printf "Launching launch.py..." printf "\n%s\n" "${delimiter}" - "${python_cmd}" "${LAUNCH_SCRIPT}" "$@" + exec "${python_cmd}" "${LAUNCH_SCRIPT}" "$@" fi |