diff options
| -rw-r--r-- | .github/ISSUE_TEMPLATE/feature_request.yml | 2 | ||||
| -rw-r--r-- | modules/api/api.py | 48 | ||||
| -rw-r--r-- | modules/api/models.py | 4 | ||||
| -rw-r--r-- | modules/processing.py | 4 | ||||
| -rw-r--r-- | modules/sd_hijack.py | 7 | ||||
| -rw-r--r-- | modules/textual_inversion/textual_inversion.py | 166 | ||||
| -rw-r--r-- | scripts/sd_upscale.py | 2 | ||||
| -rw-r--r-- | test/basic_features/img2img_test.py | 6 |
8 files changed, 163 insertions, 76 deletions
diff --git a/.github/ISSUE_TEMPLATE/feature_request.yml b/.github/ISSUE_TEMPLATE/feature_request.yml index 8ca6e21f..35a88740 100644 --- a/.github/ISSUE_TEMPLATE/feature_request.yml +++ b/.github/ISSUE_TEMPLATE/feature_request.yml @@ -1,7 +1,7 @@ name: Feature request description: Suggest an idea for this project title: "[Feature Request]: " -labels: ["suggestion"] +labels: ["enhancement"] body: - type: checkboxes diff --git a/modules/api/api.py b/modules/api/api.py index 2103709b..5b6125f8 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -11,7 +11,7 @@ from fastapi.security import HTTPBasic, HTTPBasicCredentials from secrets import compare_digest import modules.shared as shared -from modules import sd_samplers, deepbooru, sd_hijack, images +from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui from modules.api.models import * from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images from modules.extras import run_extras @@ -28,8 +28,13 @@ def upscaler_to_index(name: str): try: return [x.name.lower() for x in shared.sd_upscalers].index(name.lower()) except: - raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be on of these: {' , '.join([x.name for x in sd_upscalers])}") + raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in sd_upscalers])}") +def script_name_to_index(name, scripts): + try: + return [script.title().lower() for script in scripts].index(name.lower()) + except: + raise HTTPException(status_code=422, detail=f"Script '{name}' not found") def validate_sampler_name(name): config = sd_samplers.all_samplers_map.get(name, None) @@ -143,7 +148,21 @@ class Api: raise HTTPException(status_code=401, detail="Incorrect username or password", headers={"WWW-Authenticate": "Basic"}) + def get_script(self, script_name, script_runner): + if script_name is None: + return None, None + + if not script_runner.scripts: + script_runner.initialize_scripts(False) + ui.create_ui() + + script_idx = script_name_to_index(script_name, script_runner.selectable_scripts) + script = script_runner.selectable_scripts[script_idx] + return script, script_idx + def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI): + script, script_idx = self.get_script(txt2imgreq.script_name, scripts.scripts_txt2img) + populate = txt2imgreq.copy(update={ # Override __init__ params "sampler_name": validate_sampler_name(txt2imgreq.sampler_name or txt2imgreq.sampler_index), "do_not_save_samples": True, @@ -153,14 +172,22 @@ class Api: if populate.sampler_name: populate.sampler_index = None # prevent a warning later on + args = vars(populate) + args.pop('script_name', None) + with self.queue_lock: - p = StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **vars(populate)) + p = StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args) shared.state.begin() - processed = process_images(p) + if script is not None: + p.outpath_grids = opts.outdir_txt2img_grids + p.outpath_samples = opts.outdir_txt2img_samples + p.script_args = [script_idx + 1] + [None] * (script.args_from - 1) + p.script_args + processed = scripts.scripts_txt2img.run(p, *p.script_args) + else: + processed = process_images(p) shared.state.end() - b64images = list(map(encode_pil_to_base64, processed.images)) return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js()) @@ -170,6 +197,8 @@ class Api: if init_images is None: raise HTTPException(status_code=404, detail="Init image not found") + script, script_idx = self.get_script(img2imgreq.script_name, scripts.scripts_img2img) + mask = img2imgreq.mask if mask: mask = decode_base64_to_image(mask) @@ -186,13 +215,20 @@ class Api: args = vars(populate) args.pop('include_init_images', None) # this is meant to be done by "exclude": True in model, but it's for a reason that I cannot determine. + args.pop('script_name', None) with self.queue_lock: p = StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args) p.init_images = [decode_base64_to_image(x) for x in init_images] shared.state.begin() - processed = process_images(p) + if script is not None: + p.outpath_grids = opts.outdir_img2img_grids + p.outpath_samples = opts.outdir_img2img_samples + p.script_args = [script_idx + 1] + [None] * (script.args_from - 1) + p.script_args + processed = scripts.scripts_img2img.run(p, *p.script_args) + else: + processed = process_images(p) shared.state.end() b64images = list(map(encode_pil_to_base64, processed.images)) diff --git a/modules/api/models.py b/modules/api/models.py index 5fa63774..ce43c858 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -100,13 +100,13 @@ class PydanticModelGenerator: StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator( "StableDiffusionProcessingTxt2Img", StableDiffusionProcessingTxt2Img, - [{"key": "sampler_index", "type": str, "default": "Euler"}] + [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "script_name", "type": str, "default": None}, {"key": "script_args", "type": list, "default": []}] ).generate_model() StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator( "StableDiffusionProcessingImg2Img", StableDiffusionProcessingImg2Img, - [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}, {"key": "include_init_images", "type": bool, "default": False, "exclude" : True}] + [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}, {"key": "include_init_images", "type": bool, "default": False, "exclude" : True}, {"key": "script_name", "type": str, "default": None}, {"key": "script_args", "type": list, "default": []}] ).generate_model() class TextToImageResponse(BaseModel): diff --git a/modules/processing.py b/modules/processing.py index 82157bc9..1d23b15f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -98,7 +98,7 @@ class StableDiffusionProcessing(): """
The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
"""
- def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None):
+ def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None):
if sampler_index is not None:
print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
@@ -149,7 +149,7 @@ class StableDiffusionProcessing(): self.seed_resize_from_w = 0
self.scripts = None
- self.script_args = None
+ self.script_args = script_args
self.all_prompts = None
self.all_negative_prompts = None
self.all_seeds = None
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index cfdb09d6..6b0d95af 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -83,10 +83,12 @@ class StableDiffusionModelHijack: clip = None
optimization_method = None
- embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase(cmd_opts.embeddings_dir)
+ embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase()
- def hijack(self, m):
+ def __init__(self):
+ self.embedding_db.add_embedding_dir(cmd_opts.embeddings_dir)
+ def hijack(self, m):
if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
model_embeddings = m.cond_stage_model.roberta.embeddings
model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
@@ -117,7 +119,6 @@ class StableDiffusionModelHijack: self.layers = flatten(m)
def undo_hijack(self, m):
-
if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
m.cond_stage_model = m.cond_stage_model.wrapped
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 45882ed6..217fe9eb 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -66,17 +66,41 @@ class Embedding: return self.cached_checksum
+class DirWithTextualInversionEmbeddings:
+ def __init__(self, path):
+ self.path = path
+ self.mtime = None
+
+ def has_changed(self):
+ if not os.path.isdir(self.path):
+ return False
+
+ mt = os.path.getmtime(self.path)
+ if self.mtime is None or mt > self.mtime:
+ return True
+
+ def update(self):
+ if not os.path.isdir(self.path):
+ return
+
+ self.mtime = os.path.getmtime(self.path)
+
+
class EmbeddingDatabase:
- def __init__(self, embeddings_dir):
+ def __init__(self):
self.ids_lookup = {}
self.word_embeddings = {}
self.skipped_embeddings = {}
- self.dir_mtime = None
- self.embeddings_dir = embeddings_dir
self.expected_shape = -1
+ self.embedding_dirs = {}
- def register_embedding(self, embedding, model):
+ def add_embedding_dir(self, path):
+ self.embedding_dirs[path] = DirWithTextualInversionEmbeddings(path)
+
+ def clear_embedding_dirs(self):
+ self.embedding_dirs.clear()
+ def register_embedding(self, embedding, model):
self.word_embeddings[embedding.name] = embedding
ids = model.cond_stage_model.tokenize([embedding.name])[0]
@@ -93,65 +117,62 @@ class EmbeddingDatabase: vec = shared.sd_model.cond_stage_model.encode_embedding_init_text(",", 1)
return vec.shape[1]
- def load_textual_inversion_embeddings(self, force_reload = False):
- mt = os.path.getmtime(self.embeddings_dir)
- if not force_reload and self.dir_mtime is not None and mt <= self.dir_mtime:
- return
+ def load_from_file(self, path, filename):
+ name, ext = os.path.splitext(filename)
+ ext = ext.upper()
- self.dir_mtime = mt
- self.ids_lookup.clear()
- self.word_embeddings.clear()
- self.skipped_embeddings.clear()
- self.expected_shape = self.get_expected_shape()
-
- def process_file(path, filename):
- name, ext = os.path.splitext(filename)
- ext = ext.upper()
-
- if ext in ['.PNG', '.WEBP', '.JXL', '.AVIF']:
- embed_image = Image.open(path)
- if hasattr(embed_image, 'text') and 'sd-ti-embedding' in embed_image.text:
- data = embedding_from_b64(embed_image.text['sd-ti-embedding'])
- name = data.get('name', name)
- else:
- data = extract_image_data_embed(embed_image)
- name = data.get('name', name)
- elif ext in ['.BIN', '.PT']:
- data = torch.load(path, map_location="cpu")
- else:
+ if ext in ['.PNG', '.WEBP', '.JXL', '.AVIF']:
+ _, second_ext = os.path.splitext(name)
+ if second_ext.upper() == '.PREVIEW':
return
- # textual inversion embeddings
- if 'string_to_param' in data:
- param_dict = data['string_to_param']
- if hasattr(param_dict, '_parameters'):
- param_dict = getattr(param_dict, '_parameters') # fix for torch 1.12.1 loading saved file from torch 1.11
- assert len(param_dict) == 1, 'embedding file has multiple terms in it'
- emb = next(iter(param_dict.items()))[1]
- # diffuser concepts
- elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor:
- assert len(data.keys()) == 1, 'embedding file has multiple terms in it'
-
- emb = next(iter(data.values()))
- if len(emb.shape) == 1:
- emb = emb.unsqueeze(0)
- else:
- raise Exception(f"Couldn't identify {filename} as neither textual inversion embedding nor diffuser concept.")
-
- vec = emb.detach().to(devices.device, dtype=torch.float32)
- embedding = Embedding(vec, name)
- embedding.step = data.get('step', None)
- embedding.sd_checkpoint = data.get('sd_checkpoint', None)
- embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
- embedding.vectors = vec.shape[0]
- embedding.shape = vec.shape[-1]
-
- if self.expected_shape == -1 or self.expected_shape == embedding.shape:
- self.register_embedding(embedding, shared.sd_model)
+ embed_image = Image.open(path)
+ if hasattr(embed_image, 'text') and 'sd-ti-embedding' in embed_image.text:
+ data = embedding_from_b64(embed_image.text['sd-ti-embedding'])
+ name = data.get('name', name)
else:
- self.skipped_embeddings[name] = embedding
+ data = extract_image_data_embed(embed_image)
+ name = data.get('name', name)
+ elif ext in ['.BIN', '.PT']:
+ data = torch.load(path, map_location="cpu")
+ else:
+ return
+
+ # textual inversion embeddings
+ if 'string_to_param' in data:
+ param_dict = data['string_to_param']
+ if hasattr(param_dict, '_parameters'):
+ param_dict = getattr(param_dict, '_parameters') # fix for torch 1.12.1 loading saved file from torch 1.11
+ assert len(param_dict) == 1, 'embedding file has multiple terms in it'
+ emb = next(iter(param_dict.items()))[1]
+ # diffuser concepts
+ elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor:
+ assert len(data.keys()) == 1, 'embedding file has multiple terms in it'
+
+ emb = next(iter(data.values()))
+ if len(emb.shape) == 1:
+ emb = emb.unsqueeze(0)
+ else:
+ raise Exception(f"Couldn't identify {filename} as neither textual inversion embedding nor diffuser concept.")
+
+ vec = emb.detach().to(devices.device, dtype=torch.float32)
+ embedding = Embedding(vec, name)
+ embedding.step = data.get('step', None)
+ embedding.sd_checkpoint = data.get('sd_checkpoint', None)
+ embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
+ embedding.vectors = vec.shape[0]
+ embedding.shape = vec.shape[-1]
+
+ if self.expected_shape == -1 or self.expected_shape == embedding.shape:
+ self.register_embedding(embedding, shared.sd_model)
+ else:
+ self.skipped_embeddings[name] = embedding
- for root, dirs, fns in os.walk(self.embeddings_dir):
+ def load_from_dir(self, embdir):
+ if not os.path.isdir(embdir.path):
+ return
+
+ for root, dirs, fns in os.walk(embdir.path):
for fn in fns:
try:
fullfn = os.path.join(root, fn)
@@ -159,12 +180,32 @@ class EmbeddingDatabase: if os.stat(fullfn).st_size == 0:
continue
- process_file(fullfn, fn)
+ self.load_from_file(fullfn, fn)
except Exception:
print(f"Error loading embedding {fn}:", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
continue
+ def load_textual_inversion_embeddings(self, force_reload=False):
+ if not force_reload:
+ need_reload = False
+ for path, embdir in self.embedding_dirs.items():
+ if embdir.has_changed():
+ need_reload = True
+ break
+
+ if not need_reload:
+ return
+
+ self.ids_lookup.clear()
+ self.word_embeddings.clear()
+ self.skipped_embeddings.clear()
+ self.expected_shape = self.get_expected_shape()
+
+ for path, embdir in self.embedding_dirs.items():
+ self.load_from_dir(embdir)
+ embdir.update()
+
print(f"Textual inversion embeddings loaded({len(self.word_embeddings)}): {', '.join(self.word_embeddings.keys())}")
if len(self.skipped_embeddings) > 0:
print(f"Textual inversion embeddings skipped({len(self.skipped_embeddings)}): {', '.join(self.skipped_embeddings.keys())}")
@@ -247,14 +288,15 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat assert os.path.isfile(template_file), "Prompt template file doesn't exist"
assert steps, "Max steps is empty or 0"
assert isinstance(steps, int), "Max steps must be integer"
- assert steps > 0 , "Max steps must be positive"
+ assert steps > 0, "Max steps must be positive"
assert isinstance(save_model_every, int), "Save {name} must be integer"
- assert save_model_every >= 0 , "Save {name} must be positive or 0"
+ assert save_model_every >= 0, "Save {name} must be positive or 0"
assert isinstance(create_image_every, int), "Create image must be integer"
- assert create_image_every >= 0 , "Create image must be positive or 0"
+ assert create_image_every >= 0, "Create image must be positive or 0"
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, 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
diff --git a/scripts/sd_upscale.py b/scripts/sd_upscale.py index 9b8ffd85..332d76d9 100644 --- a/scripts/sd_upscale.py +++ b/scripts/sd_upscale.py @@ -25,6 +25,8 @@ class Script(scripts.Script): return [info, overlap, upscaler_index, scale_factor]
def run(self, p, _, overlap, upscaler_index, scale_factor):
+ if isinstance(upscaler_index, str):
+ upscaler_index = [x.name.lower() for x in shared.sd_upscalers].index(upscaler_index.lower())
processing.fix_seed(p)
upscaler = shared.sd_upscalers[upscaler_index]
diff --git a/test/basic_features/img2img_test.py b/test/basic_features/img2img_test.py index 0a9c1e8a..bd520b13 100644 --- a/test/basic_features/img2img_test.py +++ b/test/basic_features/img2img_test.py @@ -50,6 +50,12 @@ class TestImg2ImgWorking(unittest.TestCase): self.simple_img2img["mask"] = encode_pil_to_base64(Image.open(r"test/test_files/mask_basic.png")) self.assertEqual(requests.post(self.url_img2img, json=self.simple_img2img).status_code, 200) + def test_img2img_sd_upscale_performed(self): + self.simple_img2img["script_name"] = "sd upscale" + self.simple_img2img["script_args"] = ["", 8, "Lanczos", 2.0] + + self.assertEqual(requests.post(self.url_img2img, json=self.simple_img2img).status_code, 200) + if __name__ == "__main__": unittest.main() |