diff options
34 files changed, 309 insertions, 134 deletions
@@ -82,8 +82,8 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web - Use VAEs
- Estimated completion time in progress bar
- API
-- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
-- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
+- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
+- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
- [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
## Installation and Running
diff --git a/javascript/contextMenus.js b/javascript/contextMenus.js index fe67c42e..11bcce1b 100644 --- a/javascript/contextMenus.js +++ b/javascript/contextMenus.js @@ -9,7 +9,7 @@ contextMenuInit = function(){ function showContextMenu(event,element,menuEntries){
let posx = event.clientX + document.body.scrollLeft + document.documentElement.scrollLeft;
- let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop;
+ let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop;
let oldMenu = gradioApp().querySelector('#context-menu')
if(oldMenu){
@@ -61,15 +61,15 @@ contextMenuInit = function(){ }
- function appendContextMenuOption(targetEmementSelector,entryName,entryFunction){
-
- currentItems = menuSpecs.get(targetEmementSelector)
-
+ function appendContextMenuOption(targetElementSelector,entryName,entryFunction){
+
+ currentItems = menuSpecs.get(targetElementSelector)
+
if(!currentItems){
currentItems = []
- menuSpecs.set(targetEmementSelector,currentItems);
+ menuSpecs.set(targetElementSelector,currentItems);
}
- let newItem = {'id':targetEmementSelector+'_'+uid(),
+ let newItem = {'id':targetElementSelector+'_'+uid(),
'name':entryName,
'func':entryFunction,
'isNew':true}
@@ -97,7 +97,7 @@ contextMenuInit = function(){ if(source.id && source.id.indexOf('check_progress')>-1){
return
}
-
+
let oldMenu = gradioApp().querySelector('#context-menu')
if(oldMenu){
oldMenu.remove()
@@ -117,7 +117,7 @@ contextMenuInit = function(){ })
});
eventListenerApplied=true
-
+
}
return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener]
@@ -152,8 +152,8 @@ addContextMenuEventListener = initResponse[2]; generateOnRepeat('#img2img_generate','#img2img_interrupt');
})
- let cancelGenerateForever = function(){
- clearInterval(window.generateOnRepeatInterval)
+ let cancelGenerateForever = function(){
+ clearInterval(window.generateOnRepeatInterval)
}
appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever)
@@ -162,7 +162,7 @@ addContextMenuEventListener = initResponse[2]; appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever)
appendContextMenuOption('#roll','Roll three',
- function(){
+ function(){
let rollbutton = get_uiCurrentTabContent().querySelector('#roll');
setTimeout(function(){rollbutton.click()},100)
setTimeout(function(){rollbutton.click()},200)
diff --git a/javascript/hints.js b/javascript/hints.js index ab087530..a739a177 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -18,7 +18,7 @@ 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/javascript/progressbar.js b/javascript/progressbar.js index d58737c4..d6323ed9 100644 --- a/javascript/progressbar.js +++ b/javascript/progressbar.js @@ -3,7 +3,7 @@ global_progressbars = {} galleries = {} galleryObservers = {} -// this tracks laumnches of window.setTimeout for progressbar to prevent starting a new timeout when the previous is still running +// this tracks launches of window.setTimeout for progressbar to prevent starting a new timeout when the previous is still running timeoutIds = {} function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip, id_interrupt, id_preview, id_gallery){ @@ -20,21 +20,21 @@ function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip var skip = id_skip ? gradioApp().getElementById(id_skip) : null var interrupt = gradioApp().getElementById(id_interrupt) - + if(opts.show_progress_in_title && progressbar && progressbar.offsetParent){ if(progressbar.innerText){ let newtitle = '[' + progressbar.innerText.trim() + '] Stable Diffusion'; if(document.title != newtitle){ - document.title = newtitle; + document.title = newtitle; } }else{ let newtitle = 'Stable Diffusion' if(document.title != newtitle){ - document.title = newtitle; + document.title = newtitle; } } } - + if(progressbar!= null && progressbar != global_progressbars[id_progressbar]){ global_progressbars[id_progressbar] = progressbar @@ -63,7 +63,7 @@ function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip skip.style.display = "none" } interrupt.style.display = "none" - + //disconnect observer once generation finished, so user can close selected image if they want if (galleryObservers[id_gallery]) { galleryObservers[id_gallery].disconnect(); diff --git a/javascript/ui.js b/javascript/ui.js index 2cb280e5..587dd782 100644 --- a/javascript/ui.js +++ b/javascript/ui.js @@ -100,7 +100,7 @@ function create_submit_args(args){ // As it is currently, txt2img and img2img send back the previous output args (txt2img_gallery, generation_info, html_info) whenever you generate a new image. // This can lead to uploading a huge gallery of previously generated images, which leads to an unnecessary delay between submitting and beginning to generate. - // I don't know why gradio is seding outputs along with inputs, but we can prevent sending the image gallery here, which seems to be an issue for some. + // I don't know why gradio is sending outputs along with inputs, but we can prevent sending the image gallery here, which seems to be an issue for some. // If gradio at some point stops sending outputs, this may break something if(Array.isArray(res[res.length - 3])){ res[res.length - 3] = null diff --git a/modules/api/api.py b/modules/api/api.py index 89935a70..33845045 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -67,10 +67,10 @@ def encode_pil_to_base64(image): class Api: def __init__(self, app: FastAPI, queue_lock: Lock): if shared.cmd_opts.api_auth: - self.credenticals = dict() + self.credentials = dict() for auth in shared.cmd_opts.api_auth.split(","): user, password = auth.split(":") - self.credenticals[user] = password + self.credentials[user] = password self.router = APIRouter() self.app = app @@ -93,7 +93,7 @@ class Api: self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem]) self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem]) self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem]) - self.add_api_route("/sdapi/v1/prompt-styles", self.get_promp_styles, methods=["GET"], response_model=List[PromptStyleItem]) + self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem]) self.add_api_route("/sdapi/v1/artist-categories", self.get_artists_categories, methods=["GET"], response_model=List[str]) self.add_api_route("/sdapi/v1/artists", self.get_artists, methods=["GET"], response_model=List[ArtistItem]) @@ -102,9 +102,9 @@ class Api: return self.app.add_api_route(path, endpoint, dependencies=[Depends(self.auth)], **kwargs) return self.app.add_api_route(path, endpoint, **kwargs) - def auth(self, credenticals: HTTPBasicCredentials = Depends(HTTPBasic())): - if credenticals.username in self.credenticals: - if compare_digest(credenticals.password, self.credenticals[credenticals.username]): + def auth(self, credentials: HTTPBasicCredentials = Depends(HTTPBasic())): + if credentials.username in self.credentials: + if compare_digest(credentials.password, self.credentials[credentials.username]): return True raise HTTPException(status_code=401, detail="Incorrect username or password", headers={"WWW-Authenticate": "Basic"}) @@ -239,7 +239,7 @@ class Api: def interrogateapi(self, interrogatereq: InterrogateRequest): image_b64 = interrogatereq.image if image_b64 is None: - raise HTTPException(status_code=404, detail="Image not found") + raise HTTPException(status_code=404, detail="Image not found") img = decode_base64_to_image(image_b64) img = img.convert('RGB') @@ -252,7 +252,7 @@ class Api: processed = deepbooru.model.tag(img) else: raise HTTPException(status_code=404, detail="Model not found") - + return InterrogateResponse(caption=processed) def interruptapi(self): @@ -308,7 +308,7 @@ class Api: def get_realesrgan_models(self): return [{"name":x.name,"path":x.data_path, "scale":x.scale} for x in get_realesrgan_models(None)] - def get_promp_styles(self): + def get_prompt_styles(self): styleList = [] for k in shared.prompt_styles.styles: style = shared.prompt_styles.styles[k] diff --git a/modules/api/models.py b/modules/api/models.py index f77951fc..a22bc6b3 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -128,7 +128,7 @@ class ExtrasBaseRequest(BaseModel): upscaling_resize: float = Field(default=2, title="Upscaling Factor", ge=1, le=4, description="By how much to upscale the image, only used when resize_mode=0.") upscaling_resize_w: int = Field(default=512, title="Target Width", ge=1, description="Target width for the upscaler to hit. Only used when resize_mode=1.") upscaling_resize_h: int = Field(default=512, title="Target Height", ge=1, description="Target height for the upscaler to hit. Only used when resize_mode=1.") - upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the choosen size?") + upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the chosen size?") upscaler_1: str = Field(default="None", title="Main upscaler", description=f"The name of the main upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}") upscaler_2: str = Field(default="None", title="Secondary upscaler", description=f"The name of the secondary upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}") extras_upscaler_2_visibility: float = Field(default=0, title="Secondary upscaler visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of secondary upscaler, values should be between 0 and 1.") 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/extras.py b/modules/extras.py index 0ad8deec..6fa7d856 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -188,13 +188,19 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_ for op in extras_ops:
image, info = op(image, info)
- if opts.use_original_name_batch and image_name != None:
+ if opts.use_original_name_batch and image_name is not None:
basename = os.path.splitext(os.path.basename(image_name))[0]
else:
basename = ''
+ # Add upscaler name as a suffix.
+ suffix = f"-{shared.sd_upscalers[extras_upscaler_1].name}" if shared.opts.use_upscaler_name_as_suffix else ""
+ # Add second upscaler if applicable.
+ if suffix and extras_upscaler_2 and extras_upscaler_2_visibility:
+ suffix += f"-{shared.sd_upscalers[extras_upscaler_2].name}"
+
images.save_image(image, path=outpath, basename=basename, seed=None, prompt=None, extension=opts.samples_format, info=info, short_filename=True,
- no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=None)
+ no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=None, suffix=suffix)
if opts.enable_pnginfo:
image.info = existing_pnginfo
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index 565e342d..fbd91300 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -14,6 +14,7 @@ re_param_code = r'\s*([\w ]+):\s*("(?:\\|\"|[^\"])+"|[^,]*)(?:,|$)' re_param = re.compile(re_param_code)
re_params = re.compile(r"^(?:" + re_param_code + "){3,}$")
re_imagesize = re.compile(r"^(\d+)x(\d+)$")
+re_hypernet_hash = re.compile("\(([0-9a-f]+)\)$")
type_of_gr_update = type(gr.update())
paste_fields = {}
bind_list = []
@@ -139,6 +140,30 @@ def run_bind(): )
+def find_hypernetwork_key(hypernet_name, hypernet_hash=None):
+ """Determines the config parameter name to use for the hypernet based on the parameters in the infotext.
+
+ Example: an infotext provides "Hypernet: ke-ta" and "Hypernet hash: 1234abcd". For the "Hypernet" config
+ parameter this means there should be an entry that looks like "ke-ta-10000(1234abcd)" to set it to.
+
+ If the infotext has no hash, then a hypernet with the same name will be selected instead.
+ """
+ hypernet_name = hypernet_name.lower()
+ if hypernet_hash is not None:
+ # Try to match the hash in the name
+ for hypernet_key in shared.hypernetworks.keys():
+ result = re_hypernet_hash.search(hypernet_key)
+ if result is not None and result[1] == hypernet_hash:
+ return hypernet_key
+ else:
+ # Fall back to a hypernet with the same name
+ for hypernet_key in shared.hypernetworks.keys():
+ if hypernet_key.lower().startswith(hypernet_name):
+ return hypernet_key
+
+ return None
+
+
def parse_generation_parameters(x: str):
"""parses generation parameters string, the one you see in text field under the picture in UI:
```
@@ -188,6 +213,14 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model if "Clip skip" not in res:
res["Clip skip"] = "1"
+ if "Hypernet strength" not in res:
+ res["Hypernet strength"] = "1"
+
+ if "Hypernet" in res:
+ hypernet_name = res["Hypernet"]
+ hypernet_hash = res.get("Hypernet hash", None)
+ res["Hypernet"] = find_hypernetwork_key(hypernet_name, hypernet_hash)
+
return res
diff --git a/modules/images.py b/modules/images.py index 8146f580..809ad9f7 100644 --- a/modules/images.py +++ b/modules/images.py @@ -136,8 +136,19 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts): lines.append(word)
return lines
- def draw_texts(drawing, draw_x, draw_y, lines):
+ def get_font(fontsize):
+ try:
+ return ImageFont.truetype(opts.font or Roboto, fontsize)
+ except Exception:
+ return ImageFont.truetype(Roboto, fontsize)
+
+ def draw_texts(drawing, draw_x, draw_y, lines, initial_fnt, initial_fontsize):
for i, line in enumerate(lines):
+ fnt = initial_fnt
+ fontsize = initial_fontsize
+ while drawing.multiline_textsize(line.text, font=fnt)[0] > line.allowed_width and fontsize > 0:
+ fontsize -= 1
+ fnt = get_font(fontsize)
drawing.multiline_text((draw_x, draw_y + line.size[1] / 2), line.text, font=fnt, fill=color_active if line.is_active else color_inactive, anchor="mm", align="center")
if not line.is_active:
@@ -148,10 +159,7 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts): fontsize = (width + height) // 25
line_spacing = fontsize // 2
- try:
- fnt = ImageFont.truetype(opts.font or Roboto, fontsize)
- except Exception:
- fnt = ImageFont.truetype(Roboto, fontsize)
+ fnt = get_font(fontsize)
color_active = (0, 0, 0)
color_inactive = (153, 153, 153)
@@ -178,6 +186,7 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts): for line in texts:
bbox = calc_d.multiline_textbbox((0, 0), line.text, font=fnt)
line.size = (bbox[2] - bbox[0], bbox[3] - bbox[1])
+ line.allowed_width = allowed_width
hor_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing for lines in hor_texts]
ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in
@@ -194,13 +203,13 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts): x = pad_left + width * col + width / 2
y = pad_top / 2 - hor_text_heights[col] / 2
- draw_texts(d, x, y, hor_texts[col])
+ draw_texts(d, x, y, hor_texts[col], fnt, fontsize)
for row in range(rows):
x = pad_left / 2
y = pad_top + height * row + height / 2 - ver_text_heights[row] / 2
- draw_texts(d, x, y, ver_texts[row])
+ draw_texts(d, x, y, ver_texts[row], fnt, fontsize)
return result
@@ -429,7 +438,7 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i The directory to save the image. Note, the option `save_to_dirs` will make the image to be saved into a sub directory.
basename (`str`):
The base filename which will be applied to `filename pattern`.
- seed, prompt, short_filename,
+ seed, prompt, short_filename,
extension (`str`):
Image file extension, default is `png`.
pngsectionname (`str`):
@@ -590,7 +599,7 @@ def read_info_from_image(image): Negative prompt: {json_info["uc"]}
Steps: {json_info["steps"]}, Sampler: {sampler}, CFG scale: {json_info["scale"]}, Seed: {json_info["seed"]}, Size: {image.width}x{image.height}, Clip skip: 2, ENSD: 31337"""
except Exception:
- print(f"Error parsing NovelAI iamge generation parameters:", file=sys.stderr)
+ print(f"Error parsing NovelAI image generation parameters:", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
return geninfo, items
@@ -613,3 +622,14 @@ def image_data(data): pass
return '', None
+
+
+def flatten(img, bgcolor):
+ """replaces transparency with bgcolor (example: "#ffffff"), returning an RGB mode image with no transparency"""
+
+ if img.mode == "RGBA":
+ background = Image.new('RGBA', img.size, bgcolor)
+ background.paste(img, mask=img)
+ img = background
+
+ return img.convert('RGB')
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/lowvram.py b/modules/lowvram.py index aa464a95..042a0254 100644 --- a/modules/lowvram.py +++ b/modules/lowvram.py @@ -55,18 +55,20 @@ def setup_for_low_vram(sd_model, use_medvram): if hasattr(sd_model.cond_stage_model, 'model'):
sd_model.cond_stage_model.transformer = sd_model.cond_stage_model.model
- # remove three big modules, cond, first_stage, and unet from the model and then
+ # remove four big modules, cond, first_stage, depth (if applicable), and unet from the model and then
# send the model to GPU. Then put modules back. the modules will be in CPU.
- stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.model
- sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.model = None, None, None
+ stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, getattr(sd_model, 'depth_model', None), sd_model.model
+ sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.model = None, None, None, None
sd_model.to(devices.device)
- sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.model = stored
+ sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.model = stored
- # register hooks for those the first two models
+ # register hooks for those the first three models
sd_model.cond_stage_model.transformer.register_forward_pre_hook(send_me_to_gpu)
sd_model.first_stage_model.register_forward_pre_hook(send_me_to_gpu)
sd_model.first_stage_model.encode = first_stage_model_encode_wrap
sd_model.first_stage_model.decode = first_stage_model_decode_wrap
+ if sd_model.depth_model:
+ sd_model.depth_model.register_forward_pre_hook(send_me_to_gpu)
parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
if hasattr(sd_model.cond_stage_model, 'model'):
diff --git a/modules/ngrok.py b/modules/ngrok.py index 64c9a3c2..3df2c06b 100644 --- a/modules/ngrok.py +++ b/modules/ngrok.py @@ -2,7 +2,7 @@ from pyngrok import ngrok, conf, exception def connect(token, port, region): account = None - if token == None: + if token is None: token = 'None' else: if ':' in token: @@ -14,7 +14,7 @@ def connect(token, port, region): auth_token=token, region=region ) try: - if account == None: + if account is None: public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True).public_url else: public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True, auth=account).public_url diff --git a/modules/processing.py b/modules/processing.py index 24c537d1..4a406084 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -27,6 +27,7 @@ from ldm.data.util import AddMiDaS from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion
from einops import repeat, rearrange
+from blendmodes.blend import blendLayers, BlendType
# some of those options should not be changed at all because they would break the model, so I removed them from options.
opt_C = 4
@@ -39,17 +40,19 @@ def setup_color_correction(image): return correction_target
-def apply_color_correction(correction, image):
+def apply_color_correction(correction, original_image):
logging.info("Applying color correction.")
image = Image.fromarray(cv2.cvtColor(exposure.match_histograms(
cv2.cvtColor(
- np.asarray(image),
+ np.asarray(original_image),
cv2.COLOR_RGB2LAB
),
correction,
channel_axis=2
), cv2.COLOR_LAB2RGB).astype("uint8"))
-
+
+ image = blendLayers(image, original_image, BlendType.LUMINOSITY)
+
return image
@@ -77,7 +80,7 @@ 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, 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):
if sampler_index is not None:
print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
@@ -118,6 +121,7 @@ class StableDiffusionProcessing(): self.s_tmax = s_tmax or float('inf') # not representable as a standard ui option
self.s_noise = s_noise or opts.s_noise
self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts}
+ self.override_settings_restore_afterwards = override_settings_restore_afterwards
self.is_using_inpainting_conditioning = False
if not seed_enable_extras:
@@ -147,11 +151,11 @@ class StableDiffusionProcessing(): # 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))
+ 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)
+ image_conditioning = image_conditioning.to(x.dtype)
return image_conditioning
@@ -199,7 +203,7 @@ class StableDiffusionProcessing(): source_image * (1.0 - conditioning_mask),
getattr(self, "inpainting_mask_weight", shared.opts.inpainting_mask_weight)
)
-
+
# Encode the new masked image using first stage of network.
conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image))
@@ -314,7 +318,7 @@ class Processed: return json.dumps(obj)
- def infotext(self, p: StableDiffusionProcessing, index):
+ def infotext(self, p: StableDiffusionProcessing, index):
return create_infotext(p, self.all_prompts, self.all_seeds, self.all_subseeds, comments=[], position_in_batch=index % self.batch_size, iteration=index // self.batch_size)
@@ -429,6 +433,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration "Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
"Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
"Hypernet": (None if shared.loaded_hypernetwork is None else shared.loaded_hypernetwork.name),
+ "Hypernet hash": (None if shared.loaded_hypernetwork is None else sd_models.model_hash(shared.loaded_hypernetwork.filename)),
"Hypernet strength": (None if shared.loaded_hypernetwork is None or shared.opts.sd_hypernetwork_strength >= 1 else shared.opts.sd_hypernetwork_strength),
"Batch size": (None if p.batch_size < 2 else p.batch_size),
"Batch pos": (None if p.batch_size < 2 else position_in_batch),
@@ -446,7 +451,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration generation_params_text = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in generation_params.items() if v is not None])
- negative_prompt_text = "\nNegative prompt: " + p.all_negative_prompts[index] if p.all_negative_prompts[index] else ""
+ negative_prompt_text = "\nNegative prompt: " + p.all_negative_prompts[index] if p.all_negative_prompts[index] else ""
return f"{all_prompts[index]}{negative_prompt_text}\n{generation_params_text}".strip()
@@ -463,12 +468,14 @@ def process_images(p: StableDiffusionProcessing) -> Processed: res = process_images_inner(p)
- finally: # restore opts to original state
- for k, v in stored_opts.items():
- setattr(opts, k, v)
- if k == 'sd_hypernetwork': shared.reload_hypernetworks()
- if k == 'sd_model_checkpoint': sd_models.reload_model_weights()
- if k == 'sd_vae': sd_vae.reload_vae_weights()
+ finally:
+ # restore opts to original state
+ if p.override_settings_restore_afterwards:
+ for k, v in stored_opts.items():
+ setattr(opts, k, v)
+ if k == 'sd_hypernetwork': shared.reload_hypernetworks()
+ if k == 'sd_model_checkpoint': sd_models.reload_model_weights()
+ if k == 'sd_vae': sd_vae.reload_vae_weights()
return res
@@ -537,7 +544,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: for n in range(p.n_iter):
if state.skipped:
state.skipped = False
-
+
if state.interrupted:
break
@@ -612,7 +619,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: image.info["parameters"] = text
output_images.append(image)
- del x_samples_ddim
+ del x_samples_ddim
devices.torch_gc()
@@ -704,7 +711,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2]
- """saves image before applying hires fix, if enabled in options; takes as an arguyment either an image or batch with latent space images"""
+ """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
def save_intermediate(image, index):
if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix:
return
@@ -720,7 +727,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
- # Avoid making the inpainting conditioning unless necessary as
+ # Avoid making the inpainting conditioning unless necessary as
# this does need some extra compute to decode / encode the image again.
if getattr(self, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) < 1.0:
image_conditioning = self.img2img_image_conditioning(decode_first_stage(self.sd_model, samples), samples)
@@ -829,9 +836,9 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.color_corrections = []
imgs = []
for img in self.init_images:
- image = img.convert("RGB")
+ image = images.flatten(img, opts.img2img_background_color)
- if crop_region is None:
+ if crop_region is None and self.resize_mode != 3:
image = images.resize_image(self.resize_mode, image, self.width, self.height)
if image_mask is not None:
@@ -840,6 +847,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.overlay_images.append(image_masked.convert('RGBA'))
+ # crop_region is not None if we are doing inpaint full res
if crop_region is not None:
image = image.crop(crop_region)
image = images.resize_image(2, image, self.width, self.height)
@@ -876,6 +884,9 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))
+ if self.resize_mode == 3:
+ self.init_latent = torch.nn.functional.interpolate(self.init_latent, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
+
if image_mask is not None:
init_mask = latent_mask
latmask = init_mask.convert('RGB').resize((self.init_latent.shape[3], self.init_latent.shape[2]))
diff --git a/modules/safe.py b/modules/safe.py index 10460ad0..479c8b86 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':
@@ -80,7 +80,7 @@ def check_pt(filename, extra_handler): # new pytorch format is a zip file
with zipfile.ZipFile(filename) as z:
check_zip_filenames(filename, z.namelist())
-
+
# find filename of data.pkl in zip file: '<directory name>/data.pkl'
data_pkl_filenames = [f for f in z.namelist() if data_pkl_re.match(f)]
if len(data_pkl_filenames) == 0:
@@ -108,7 +108,7 @@ def load(filename, *args, **kwargs): def load_with_extra(filename, extra_handler=None, *args, **kwargs):
"""
- this functon is intended to be used by extensions that want to load models with
+ this function is intended to be used by extensions that want to load models with
some extra classes in them that the usual unpickler would find suspicious.
Use the extra_handler argument to specify a function that takes module and field name as text,
diff --git a/modules/scripts.py b/modules/scripts.py index 23ca195d..722f8685 100644 --- a/modules/scripts.py +++ b/modules/scripts.py @@ -36,7 +36,7 @@ class Script: def ui(self, is_img2img):
"""this function should create gradio UI elements. See https://gradio.app/docs/#components
The return value should be an array of all components that are used in processing.
- Values of those returned componenbts will be passed to run() and process() functions.
+ Values of those returned components will be passed to run() and process() functions.
"""
pass
@@ -47,7 +47,7 @@ class Script: This function should return:
- False if the script should not be shown in UI at all
- - True if the script should be shown in UI if it's scelected in the scripts drowpdown
+ - True if the script should be shown in UI if it's selected in the scripts dropdown
- script.AlwaysVisible if the script should be shown in UI at all times
"""
diff --git a/modules/sd_hijack_inpainting.py b/modules/sd_hijack_inpainting.py index 938f9a58..85e7281f 100644 --- a/modules/sd_hijack_inpainting.py +++ b/modules/sd_hijack_inpainting.py @@ -209,7 +209,7 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F else: x_in = torch.cat([x] * 2) t_in = torch.cat([t] * 2) - + if isinstance(c, dict): assert isinstance(unconditional_conditioning, dict) c_in = dict() @@ -278,7 +278,7 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t_prime, index) return x_prev, pred_x0, e_t - + # ================================================================================================= # Monkey patch LatentInpaintDiffusion to load the checkpoint with a proper config. # Adapted from: @@ -324,12 +324,11 @@ def should_hijack_inpainting(checkpoint_info): def do_inpainting_hijack(): # most of this stuff seems to no longer be needed because it is already included into SD2.0 - # LatentInpaintDiffusion remains because SD2.0's LatentInpaintDiffusion can't be loaded without specifying a checkpoint # p_sample_plms is needed because PLMS can't work with dicts as conditionings - # this file should be cleaned up later if weverything tuens out to work fine + # this file should be cleaned up later if everything turns out to work fine # ldm.models.diffusion.ddpm.get_unconditional_conditioning = get_unconditional_conditioning - ldm.models.diffusion.ddpm.LatentInpaintDiffusion = LatentInpaintDiffusion + # ldm.models.diffusion.ddpm.LatentInpaintDiffusion = LatentInpaintDiffusion # ldm.models.diffusion.ddim.DDIMSampler.p_sample_ddim = p_sample_ddim # ldm.models.diffusion.ddim.DDIMSampler.sample = sample_ddim 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_hijack_unet.py b/modules/sd_hijack_unet.py index 1b9d7757..18daf8c1 100644 --- a/modules/sd_hijack_unet.py +++ b/modules/sd_hijack_unet.py @@ -4,7 +4,7 @@ import torch class TorchHijackForUnet:
"""
This is torch, but with cat that resizes tensors to appropriate dimensions if they do not match;
- this makes it possible to create pictures with dimensions that are muliples of 8 rather than 64
+ this makes it possible to create pictures with dimensions that are multiples of 8 rather than 64
"""
def __getattr__(self, item):
diff --git a/modules/sd_models.py b/modules/sd_models.py index 5b37f3fe..f36b299f 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -293,13 +293,16 @@ def load_model(checkpoint_info=None): if should_hijack_inpainting(checkpoint_info):
# Hardcoded config for now...
sd_config.model.target = "ldm.models.diffusion.ddpm.LatentInpaintDiffusion"
- sd_config.model.params.use_ema = False
sd_config.model.params.conditioning_key = "hybrid"
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_info.config.replace(".yaml", "-inpainting.yaml"))
+ if not hasattr(sd_config.model.params, "use_ema"):
+ sd_config.model.params.use_ema = False
+
do_inpainting_hijack()
if shared.cmd_opts.no_half:
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/modules/shared.py b/modules/shared.py index 272267c1..8ea3b441 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -5,6 +5,7 @@ import os import sys
import time
+from PIL import Image
import gradio as gr
import tqdm
@@ -293,6 +294,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "export_for_4chan": OptionInfo(True, "If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG"),
"use_original_name_batch": OptionInfo(False, "Use original name for output filename during batch process in extras tab"),
+ "use_upscaler_name_as_suffix": OptionInfo(False, "Use upscaler name as filename suffix in the extras tab"),
"save_selected_only": OptionInfo(True, "When using 'Save' button, only save a single selected image"),
"do_not_add_watermark": OptionInfo(False, "Do not add watermark to images"),
@@ -362,6 +364,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.5, "maximum": 1.5, "step": 0.01 }),
"img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."),
"img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."),
+ "img2img_background_color": OptionInfo("#ffffff", "With img2img, fill image's transparent parts with this color.", gr.ColorPicker, {}),
"enable_quantization": OptionInfo(False, "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply."),
"enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"),
"use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index 2dc64c3c..88d68c76 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -28,9 +28,9 @@ class DatasetEntry: class PersonalizedBase(Dataset):
- def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once'):
+ def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once'):
re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex) > 0 else None
-
+
self.placeholder_token = placeholder_token
self.width = width
@@ -50,14 +50,14 @@ class PersonalizedBase(Dataset): self.image_paths = [os.path.join(data_root, file_path) for file_path in os.listdir(data_root)]
-
+
self.shuffle_tags = shuffle_tags
self.tag_drop_out = tag_drop_out
print("Preparing dataset...")
for path in tqdm.tqdm(self.image_paths):
if shared.state.interrupted:
- raise Exception("inturrupted")
+ raise Exception("interrupted")
try:
image = Image.open(path).convert('RGB').resize((self.width, self.height), PIL.Image.BICUBIC)
except Exception:
@@ -144,7 +144,7 @@ class PersonalizedDataLoader(DataLoader): self.collate_fn = collate_wrapper_random
else:
self.collate_fn = collate_wrapper
-
+
class BatchLoader:
def __init__(self, data):
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index e28c357a..daf3997b 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -133,7 +133,7 @@ class EmbeddingDatabase: process_file(fullfn, fn)
except Exception:
- print(f"Error loading emedding {fn}:", file=sys.stderr)
+ print(f"Error loading embedding {fn}:", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
continue
@@ -194,7 +194,7 @@ def write_loss(log_directory, filename, step, epoch_len, values): csv_writer.writeheader()
epoch = (step - 1) // epoch_len
- epoch_step = (step - 1) % epoch_len
+ epoch_step = (step - 1) % epoch_len
csv_writer.writerow({
"step": step,
@@ -270,9 +270,9 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ # 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
-
+
pin_memory = shared.opts.pin_memory
-
+
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method)
latent_sampling_method = ds.latent_sampling_method
@@ -295,12 +295,12 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ loss_step = 0
_loss_step = 0 #internal
-
+
last_saved_file = "<none>"
last_saved_image = "<none>"
forced_filename = "<none>"
embedding_yet_to_be_embedded = False
-
+
pbar = tqdm.tqdm(total=steps - initial_step)
try:
for i in range((steps-initial_step) * gradient_step):
@@ -327,10 +327,10 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ c = shared.sd_model.cond_stage_model(batch.cond_text)
loss = shared.sd_model(x, c)[0] / gradient_step
del x
-
+
_loss_step += loss.item()
scaler.scale(loss).backward()
-
+
# go back until we reach gradient accumulation steps
if (j + 1) % gradient_step != 0:
continue
diff --git a/modules/ui.py b/modules/ui.py index 28481e33..9dec61d5 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -49,10 +49,14 @@ if not cmd_opts.share and not cmd_opts.listen: gradio.utils.version_check = lambda: None
gradio.utils.get_local_ip_address = lambda: '127.0.0.1'
-if cmd_opts.ngrok != None:
+if cmd_opts.ngrok is not None:
import modules.ngrok as ngrok
print('ngrok authtoken detected, trying to connect...')
- ngrok.connect(cmd_opts.ngrok, cmd_opts.port if cmd_opts.port != None else 7860, cmd_opts.ngrok_region)
+ ngrok.connect(
+ cmd_opts.ngrok,
+ cmd_opts.port if cmd_opts.port is not None else 7860,
+ cmd_opts.ngrok_region
+ )
def gr_show(visible=True):
@@ -812,7 +816,7 @@ def create_ui(): with gr.Tabs(elem_id="mode_img2img") as tabs_img2img_mode:
with gr.TabItem('img2img', id='img2img'):
- init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool=cmd_opts.gradio_img2img_tool).style(height=480)
+ init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool=cmd_opts.gradio_img2img_tool, image_mode="RGBA").style(height=480)
with gr.TabItem('Inpaint', id='inpaint'):
init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool=cmd_opts.gradio_inpaint_tool, image_mode="RGBA").style(height=480)
@@ -853,7 +857,7 @@ def create_ui(): img2img_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs)
with gr.Row():
- resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", show_label=False, choices=["Just resize", "Crop and resize", "Resize and fill"], type="index", value="Just resize")
+ resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", show_label=False, choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
steps = gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=20)
sampler_index = gr.Radio(label='Sampling method', choices=[x.name for x in samplers_for_img2img], value=samplers_for_img2img[0].name, type="index")
diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py index 1434f25f..eec9586f 100644 --- a/modules/ui_extensions.py +++ b/modules/ui_extensions.py @@ -9,6 +9,8 @@ import git import gradio as gr
import html
+import shutil
+import errno
from modules import extensions, shared, paths
@@ -138,7 +140,18 @@ def install_extension_from_url(dirname, url): repo = git.Repo.clone_from(url, tmpdir)
repo.remote().fetch()
- os.rename(tmpdir, target_dir)
+ try:
+ os.rename(tmpdir, target_dir)
+ except OSError as err:
+ # TODO what does this do on windows? I think it'll be a different error code but I don't have a system to check it
+ # Shouldn't cause any new issues at least but we probably want to handle it there too.
+ if err.errno == errno.EXDEV:
+ # Cross device link, typical in docker or when tmp/ and extensions/ are on different file systems
+ # Since we can't use a rename, do the slower but more versitile shutil.move()
+ shutil.move(tmpdir, target_dir)
+ else:
+ # Something else, not enough free space, permissions, etc. rethrow it so that it gets handled.
+ raise(err)
import launch
launch.run_extension_installer(target_dir)
diff --git a/requirements.txt b/requirements.txt index 678acb4d..5bed694e 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,3 +1,4 @@ +blendmodes
accelerate
basicsr
fairscale==0.4.4
diff --git a/requirements_versions.txt b/requirements_versions.txt index 185cd066..c126c8c4 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -1,3 +1,4 @@ +blendmodes==2022
transformers==4.19.2
accelerate==0.12.0
basicsr==1.4.2
@@ -26,3 +27,4 @@ inflection==0.5.1 GitPython==3.1.27
torchsde==0.2.5
safetensors==0.2.5
+httpcore<=0.15
diff --git a/scripts/prompt_matrix.py b/scripts/prompt_matrix.py index c53ca28c..4c79eaef 100644 --- a/scripts/prompt_matrix.py +++ b/scripts/prompt_matrix.py @@ -18,7 +18,7 @@ def draw_xy_grid(xs, ys, x_label, y_label, cell): ver_texts = [[images.GridAnnotation(y_label(y))] for y in ys]
hor_texts = [[images.GridAnnotation(x_label(x))] for x in xs]
- first_pocessed = None
+ first_processed = None
state.job_count = len(xs) * len(ys)
@@ -27,17 +27,17 @@ def draw_xy_grid(xs, ys, x_label, y_label, cell): state.job = f"{ix + iy * len(xs) + 1} out of {len(xs) * len(ys)}"
processed = cell(x, y)
- if first_pocessed is None:
- first_pocessed = processed
+ if first_processed is None:
+ first_processed = processed
res.append(processed.images[0])
grid = images.image_grid(res, rows=len(ys))
grid = images.draw_grid_annotations(grid, res[0].width, res[0].height, hor_texts, ver_texts)
- first_pocessed.images = [grid]
+ first_processed.images = [grid]
- return first_pocessed
+ return first_processed
class Script(scripts.Script):
diff --git a/scripts/prompts_from_file.py b/scripts/prompts_from_file.py index 32fe6bdb..6e118ddb 100644 --- a/scripts/prompts_from_file.py +++ b/scripts/prompts_from_file.py @@ -9,6 +9,7 @@ import shlex import modules.scripts as scripts
import gradio as gr
+from modules import sd_samplers
from modules.processing import Processed, process_images
from PIL import Image
from modules.shared import opts, cmd_opts, state
@@ -44,6 +45,7 @@ prompt_tags = { "seed_resize_from_h": process_int_tag,
"seed_resize_from_w": process_int_tag,
"sampler_index": process_int_tag,
+ "sampler_name": process_string_tag,
"batch_size": process_int_tag,
"n_iter": process_int_tag,
"steps": process_int_tag,
@@ -66,14 +68,28 @@ def cmdargs(line): arg = args[pos]
assert arg.startswith("--"), f'must start with "--": {arg}'
+ assert pos+1 < len(args), f'missing argument for command line option {arg}'
+
tag = arg[2:]
+ if tag == "prompt" or tag == "negative_prompt":
+ pos += 1
+ prompt = args[pos]
+ pos += 1
+ while pos < len(args) and not args[pos].startswith("--"):
+ prompt += " "
+ prompt += args[pos]
+ pos += 1
+ res[tag] = prompt
+ continue
+
+
func = prompt_tags.get(tag, None)
assert func, f'unknown commandline option: {arg}'
- assert pos+1 < len(args), f'missing argument for command line option {arg}'
-
val = args[pos+1]
+ if tag == "sampler_name":
+ val = sd_samplers.samplers_map.get(val.lower(), None)
res[tag] = func(val)
diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index d402c281..3e0b2805 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -10,13 +10,16 @@ import numpy as np import modules.scripts as scripts
import gradio as gr
-from modules import images, sd_samplers
+from modules import images, paths, sd_samplers
from modules.hypernetworks import hypernetwork
from modules.processing import process_images, Processed, StableDiffusionProcessingTxt2Img
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
import modules.sd_samplers
import modules.sd_models
+import modules.sd_vae
+import glob
+import os
import re
@@ -114,6 +117,38 @@ def apply_clip_skip(p, x, xs): opts.data["CLIP_stop_at_last_layers"] = x
+def apply_upscale_latent_space(p, x, xs):
+ if x.lower().strip() != '0':
+ opts.data["use_scale_latent_for_hires_fix"] = True
+ else:
+ opts.data["use_scale_latent_for_hires_fix"] = False
+
+
+def find_vae(name: str):
+ if name.lower() in ['auto', 'none']:
+ return name
+ else:
+ vae_path = os.path.abspath(os.path.join(paths.models_path, 'VAE'))
+ found = glob.glob(os.path.join(vae_path, f'**/{name}.*pt'), recursive=True)
+ if found:
+ return found[0]
+ else:
+ return 'auto'
+
+
+def apply_vae(p, x, xs):
+ if x.lower().strip() == 'none':
+ modules.sd_vae.reload_vae_weights(shared.sd_model, vae_file='None')
+ else:
+ found = find_vae(x)
+ if found:
+ v = modules.sd_vae.reload_vae_weights(shared.sd_model, vae_file=found)
+
+
+def apply_styles(p: StableDiffusionProcessingTxt2Img, x: str, _):
+ p.styles = x.split(',')
+
+
def format_value_add_label(p, opt, x):
if type(x) == float:
x = round(x, 8)
@@ -167,7 +202,10 @@ axis_options = [ AxisOption("Eta", float, apply_field("eta"), format_value_add_label, None),
AxisOption("Clip skip", int, apply_clip_skip, format_value_add_label, None),
AxisOption("Denoising", float, apply_field("denoising_strength"), format_value_add_label, None),
+ AxisOption("Upscale latent space for hires.", str, apply_upscale_latent_space, format_value_add_label, None),
AxisOption("Cond. Image Mask Weight", float, apply_field("inpainting_mask_weight"), format_value_add_label, None),
+ AxisOption("VAE", str, apply_vae, format_value_add_label, None),
+ AxisOption("Styles", str, apply_styles, format_value_add_label, None),
]
@@ -229,14 +267,18 @@ class SharedSettingsStackHelper(object): self.CLIP_stop_at_last_layers = opts.CLIP_stop_at_last_layers
self.hypernetwork = opts.sd_hypernetwork
self.model = shared.sd_model
+ self.use_scale_latent_for_hires_fix = opts.use_scale_latent_for_hires_fix
+ self.vae = opts.sd_vae
def __exit__(self, exc_type, exc_value, tb):
modules.sd_models.reload_model_weights(self.model)
+ modules.sd_vae.reload_vae_weights(self.model, vae_file=find_vae(self.vae))
hypernetwork.load_hypernetwork(self.hypernetwork)
hypernetwork.apply_strength()
opts.data["CLIP_stop_at_last_layers"] = self.CLIP_stop_at_last_layers
+ opts.data["use_scale_latent_for_hires_fix"] = self.use_scale_latent_for_hires_fix
re_range = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\(([+-]\d+)\s*\))?\s*")
@@ -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
@@ -153,8 +154,8 @@ def webui(): # gradio uses a very open CORS policy via app.user_middleware, which makes it possible for
# an attacker to trick the user into opening a malicious HTML page, which makes a request to the
- # running web ui and do whatever the attcker wants, including installing an extension and
- # runnnig its code. We disable this here. Suggested by RyotaK.
+ # running web ui and do whatever the attacker wants, including installing an extension and
+ # running its code. We disable this here. Suggested by RyotaK.
app.user_middleware = [x for x in app.user_middleware if x.cls.__name__ != 'CORSMiddleware']
setup_cors(app)
@@ -1,4 +1,4 @@ -#!/bin/bash +#!/usr/bin/env bash ################################################# # Please do not make any changes to this file, # # change the variables in webui-user.sh instead # |