aboutsummaryrefslogtreecommitdiff
path: root/modules
diff options
context:
space:
mode:
Diffstat (limited to 'modules')
-rw-r--r--modules/api/api.py18
-rw-r--r--modules/api/models.py2
-rw-r--r--modules/devices.py9
-rw-r--r--modules/extras.py8
-rw-r--r--modules/images.py38
-rw-r--r--modules/import_hook.py5
-rw-r--r--modules/lowvram.py12
-rw-r--r--modules/processing.py13
-rw-r--r--modules/safe.py16
-rw-r--r--modules/scripts.py4
-rw-r--r--modules/sd_hijack_inpainting.py9
-rw-r--r--modules/sd_hijack_optimizations.py10
-rw-r--r--modules/sd_hijack_unet.py2
-rw-r--r--modules/sd_models.py5
-rw-r--r--modules/sd_samplers.py29
-rw-r--r--modules/shared.py2
-rw-r--r--modules/textual_inversion/dataset.py10
-rw-r--r--modules/textual_inversion/textual_inversion.py16
-rw-r--r--modules/ui.py2
-rw-r--r--modules/ui_extensions.py15
20 files changed, 146 insertions, 79 deletions
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..704e5165 100644
--- a/modules/extras.py
+++ b/modules/extras.py
@@ -193,8 +193,14 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
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/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/processing.py b/modules/processing.py
index f7335da2..6aa4f2cc 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
@@ -707,7 +710,7 @@ 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
@@ -832,7 +835,7 @@ 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:
image = images.resize_image(self.resize_mode, image, self.width, self.height)
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..dcce9299 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -293,6 +293,7 @@ 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 +363,7 @@ 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..76919b0f 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -812,7 +812,7 @@ 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)
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)
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-21 19:31:24 +0000