aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--javascript/hints.js2
-rw-r--r--modules/devices.py9
-rw-r--r--modules/import_hook.py5
-rw-r--r--modules/safe.py12
-rw-r--r--modules/sd_hijack_optimizations.py10
-rw-r--r--modules/sd_samplers.py29
-rw-r--r--requirements_versions.txt1
-rw-r--r--webui.py1
8 files changed, 45 insertions, 24 deletions
diff --git a/javascript/hints.js b/javascript/hints.js
index 47e24616..28e1651b 100644
--- a/javascript/hints.js
+++ b/javascript/hints.js
@@ -17,7 +17,7 @@ titles = {
"\u2199\ufe0f": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
"\u{1f4c2}": "Open images output directory",
"\u{1f4be}": "Save style",
- "\U0001F5D1": "Clear prompt"
+ "\U0001F5D1": "Clear prompt",
"\u{1f4cb}": "Apply selected styles to current prompt",
"Inpaint a part of image": "Draw a mask over an image, and the script will regenerate the masked area with content according to prompt",
diff --git a/modules/devices.py b/modules/devices.py
index f8cffae1..800510b7 100644
--- a/modules/devices.py
+++ b/modules/devices.py
@@ -125,7 +125,16 @@ def layer_norm_fix(*args, **kwargs):
return orig_layer_norm(*args, **kwargs)
+# MPS workaround for https://github.com/pytorch/pytorch/issues/90532
+orig_tensor_numpy = torch.Tensor.numpy
+def numpy_fix(self, *args, **kwargs):
+ if self.requires_grad:
+ self = self.detach()
+ return orig_tensor_numpy(self, *args, **kwargs)
+
+
# PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working
if has_mps() and version.parse(torch.__version__) < version.parse("1.13"):
torch.Tensor.to = tensor_to_fix
torch.nn.functional.layer_norm = layer_norm_fix
+ torch.Tensor.numpy = numpy_fix
diff --git a/modules/import_hook.py b/modules/import_hook.py
new file mode 100644
index 00000000..28c67dfa
--- /dev/null
+++ b/modules/import_hook.py
@@ -0,0 +1,5 @@
+import sys
+
+# this will break any attempt to import xformers which will prevent stability diffusion repo from trying to use it
+if "--xformers" not in "".join(sys.argv):
+ sys.modules["xformers"] = None
diff --git a/modules/safe.py b/modules/safe.py
index 10460ad0..7c89c4c2 100644
--- a/modules/safe.py
+++ b/modules/safe.py
@@ -37,16 +37,16 @@ class RestrictedUnpickler(pickle.Unpickler):
if module == 'collections' and name == 'OrderedDict':
return getattr(collections, name)
- if module == 'torch._utils' and name in ['_rebuild_tensor_v2', '_rebuild_parameter']:
+ if module == 'torch._utils' and name in ['_rebuild_tensor_v2', '_rebuild_parameter', '_rebuild_device_tensor_from_numpy']:
return getattr(torch._utils, name)
- if module == 'torch' and name in ['FloatStorage', 'HalfStorage', 'IntStorage', 'LongStorage', 'DoubleStorage', 'ByteStorage']:
+ if module == 'torch' and name in ['FloatStorage', 'HalfStorage', 'IntStorage', 'LongStorage', 'DoubleStorage', 'ByteStorage', 'float32']:
return getattr(torch, name)
if module == 'torch.nn.modules.container' and name in ['ParameterDict']:
return getattr(torch.nn.modules.container, name)
- if module == 'numpy.core.multiarray' and name == 'scalar':
- return numpy.core.multiarray.scalar
- if module == 'numpy' and name == 'dtype':
- return numpy.dtype
+ if module == 'numpy.core.multiarray' and name in ['scalar', '_reconstruct']:
+ return getattr(numpy.core.multiarray, name)
+ if module == 'numpy' and name in ['dtype', 'ndarray']:
+ return getattr(numpy, name)
if module == '_codecs' and name == 'encode':
return encode
if module == "pytorch_lightning.callbacks" and name == 'model_checkpoint':
diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py
index 98123fbf..02c87f40 100644
--- a/modules/sd_hijack_optimizations.py
+++ b/modules/sd_hijack_optimizations.py
@@ -127,7 +127,7 @@ def check_for_psutil():
invokeAI_mps_available = check_for_psutil()
-# -- Taken from https://github.com/invoke-ai/InvokeAI --
+# -- Taken from https://github.com/invoke-ai/InvokeAI and modified --
if invokeAI_mps_available:
import psutil
mem_total_gb = psutil.virtual_memory().total // (1 << 30)
@@ -152,14 +152,16 @@ def einsum_op_slice_1(q, k, v, slice_size):
return r
def einsum_op_mps_v1(q, k, v):
- if q.shape[1] <= 4096: # (512x512) max q.shape[1]: 4096
+ if q.shape[0] * q.shape[1] <= 2**16: # (512x512) max q.shape[1]: 4096
return einsum_op_compvis(q, k, v)
else:
slice_size = math.floor(2**30 / (q.shape[0] * q.shape[1]))
+ if slice_size % 4096 == 0:
+ slice_size -= 1
return einsum_op_slice_1(q, k, v, slice_size)
def einsum_op_mps_v2(q, k, v):
- if mem_total_gb > 8 and q.shape[1] <= 4096:
+ if mem_total_gb > 8 and q.shape[0] * q.shape[1] <= 2**16:
return einsum_op_compvis(q, k, v)
else:
return einsum_op_slice_0(q, k, v, 1)
@@ -188,7 +190,7 @@ def einsum_op(q, k, v):
return einsum_op_cuda(q, k, v)
if q.device.type == 'mps':
- if mem_total_gb >= 32:
+ if mem_total_gb >= 32 and q.shape[0] % 32 != 0 and q.shape[0] * q.shape[1] < 2**18:
return einsum_op_mps_v1(q, k, v)
return einsum_op_mps_v2(q, k, v)
diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py
index 4c123d3b..d26e48dc 100644
--- a/modules/sd_samplers.py
+++ b/modules/sd_samplers.py
@@ -23,16 +23,16 @@ samplers_k_diffusion = [
('Euler', 'sample_euler', ['k_euler'], {}),
('LMS', 'sample_lms', ['k_lms'], {}),
('Heun', 'sample_heun', ['k_heun'], {}),
- ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {}),
- ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {}),
+ ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True}),
+ ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True}),
('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}),
('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {}),
('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}),
('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}),
('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
- ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras'}),
- ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras'}),
+ ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}),
+ ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}),
('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}),
('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),
('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras'}),
@@ -444,9 +444,7 @@ class KDiffusionSampler:
return extra_params_kwargs
- def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
- steps, t_enc = setup_img2img_steps(p, steps)
-
+ def get_sigmas(self, p, steps):
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':
@@ -454,6 +452,16 @@ 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):
+ sigmas = torch.cat([sigmas[:-2], sigmas[-1:]])
+
+ return sigmas
+
+ def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
+ steps, t_enc = setup_img2img_steps(p, steps)
+
+ sigmas = self.get_sigmas(p, steps)
+
sigma_sched = sigmas[steps - t_enc - 1:]
xi = x + noise * sigma_sched[0]
@@ -485,12 +493,7 @@ class KDiffusionSampler:
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning = None):
steps = steps or p.steps
- 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':
- sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=0.1, sigma_max=10, device=shared.device)
- else:
- sigmas = self.model_wrap.get_sigmas(steps)
+ sigmas = self.get_sigmas(p, steps)
x = x * sigmas[0]
diff --git a/requirements_versions.txt b/requirements_versions.txt
index 185cd066..7208aeba 100644
--- a/requirements_versions.txt
+++ b/requirements_versions.txt
@@ -26,3 +26,4 @@ inflection==0.5.1
GitPython==3.1.27
torchsde==0.2.5
safetensors==0.2.5
+httpcore<=0.15
diff --git a/webui.py b/webui.py
index c2d0c6be..18ee5a3d 100644
--- a/webui.py
+++ b/webui.py
@@ -8,6 +8,7 @@ from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from fastapi.middleware.gzip import GZipMiddleware
+from modules import import_hook
from modules.call_queue import wrap_queued_call, queue_lock, wrap_gradio_gpu_call
from modules.paths import script_path
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-24 02:37:25 +0000