diff options
Diffstat (limited to 'modules')
| -rw-r--r-- | modules/api/api.py | 16 | ||||
| -rw-r--r-- | modules/api/models.py | 1 | ||||
| -rw-r--r-- | modules/shared.py | 2 | ||||
| -rw-r--r-- | modules/textual_inversion/dataset.py | 7 |
4 files changed, 23 insertions, 3 deletions
diff --git a/modules/api/api.py b/modules/api/api.py index 688469ad..596a6616 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -15,6 +15,9 @@ from modules.sd_models import checkpoints_list from modules.realesrgan_model import get_realesrgan_models from typing import List +if shared.cmd_opts.deepdanbooru: + from modules.deepbooru import get_deepbooru_tags + def upscaler_to_index(name: str): try: return [x.name.lower() for x in shared.sd_upscalers].index(name.lower()) @@ -220,11 +223,20 @@ class Api: if image_b64 is None: raise HTTPException(status_code=404, detail="Image not found") - img = self.__base64_to_image(image_b64) + img = decode_base64_to_image(image_b64) + img = img.convert('RGB') # Override object param with self.queue_lock: - processed = shared.interrogator.interrogate(img) + if interrogatereq.model == "clip": + processed = shared.interrogator.interrogate(img) + elif interrogatereq.model == "deepdanbooru": + if shared.cmd_opts.deepdanbooru: + processed = get_deepbooru_tags(img) + else: + raise HTTPException(status_code=404, detail="Model not found. Add --deepdanbooru when launching for using the model.") + else: + raise HTTPException(status_code=404, detail="Model not found") return InterrogateResponse(caption=processed) diff --git a/modules/api/models.py b/modules/api/models.py index 34dbfa16..f9cd929e 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -170,6 +170,7 @@ class ProgressResponse(BaseModel): class InterrogateRequest(BaseModel): image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.") + model: str = Field(default="clip", title="Model", description="The interrogate model used.") class InterrogateResponse(BaseModel): caption: str = Field(default=None, title="Caption", description="The generated caption for the image.") diff --git a/modules/shared.py b/modules/shared.py index e8bacd3c..caabf078 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -319,6 +319,8 @@ options_templates.update(options_section(('system', "System"), { options_templates.update(options_section(('training', "Training"), {
"unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training if possible. Saves VRAM."),
+ "shuffle_tags": OptionInfo(False, "Shuffleing tags by ',' when create texts."),
+ "tag_drop_out": OptionInfo(0, "Dropout tags when create texts", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.1}),
"save_optimizer_state": OptionInfo(False, "Saves Optimizer state as separate *.optim file. Training can be resumed with HN itself and matching optim file."),
"dataset_filename_word_regex": OptionInfo("", "Filename word regex"),
"dataset_filename_join_string": OptionInfo(" ", "Filename join string"),
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index ad726577..eb75c376 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -98,7 +98,12 @@ class PersonalizedBase(Dataset): def create_text(self, filename_text):
text = random.choice(self.lines)
text = text.replace("[name]", self.placeholder_token)
- text = text.replace("[filewords]", filename_text)
+ tags = filename_text.split(',')
+ if shared.opts.tag_drop_out != 0:
+ tags = [t for t in tags if random.random() > shared.opts.tag_drop_out]
+ if shared.opts.shuffle_tags:
+ random.shuffle(tags)
+ text = text.replace("[filewords]", ','.join(tags))
return text
def __len__(self):
|