diff options
86 files changed, 366 insertions, 398 deletions
diff --git a/CHANGELOG.md b/CHANGELOG.md index c56d3a0e..cf3fef3d 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,8 +8,13 @@ * Lora: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active
* Lora: Fix some Loras not working (ones that have 3x3 convolution layer)
* Lora: add an option to use old method of applying loras (producing same results as with kohya-ss)
+ * add version to infotext, footer and console output when starting
+ * add links to wiki for filename pattern settings
+ * add extended info for quicksettings setting and use multiselect input instead of a text field
### Minor:
+ * gradio bumped to 3.29.0
+ * torch bumped to 2.0.1
* --subpath option for gradio for use with reverse proxy
* linux/OSX: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)
* possible frontend optimization: do not apply localizations if there are none
@@ -17,9 +22,12 @@ * print error to console when batch processing in img2img fails
* create HTML for extra network pages only on demand
* allow directories starting with . to still list their models for lora, checkpoints, etc
+ * put infotext options into their own category in settings tab
+ * do not show licenses page when user selects Show all pages in settings
### Extensions:
* Tooltip localization support
+ * Add api method to get LoRA models with prompt
### Bug Fixes:
* re-add /docs endpoint
@@ -28,6 +36,10 @@ * fix squished thumbnails in extras tab
* keep "search" filter for extra networks when user refreshes the tab (previously it showed everthing after you refreshed)
* fix webui showing the same image if you configure the generation to always save results into same file
+ * fix bug with upscalers not working properly
+ * Fix MPS on PyTorch 2.0.1, Intel Macs
+ * make it so that custom context menu from contextMenu.js only disappears after user's click, ignoring non-user click events
+ * prevent Reload UI button/link from reloading the page when it's not yet ready
## 1.1.1
diff --git a/extensions-builtin/LDSR/ldsr_model_arch.py b/extensions-builtin/LDSR/ldsr_model_arch.py index bc11cc6e..a5fb8907 100644 --- a/extensions-builtin/LDSR/ldsr_model_arch.py +++ b/extensions-builtin/LDSR/ldsr_model_arch.py @@ -110,7 +110,6 @@ class LDSR: diffusion_steps = int(steps) eta = 1.0 - down_sample_method = 'Lanczos' gc.collect() if torch.cuda.is_available: @@ -244,7 +243,7 @@ def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True) log["sample_noquant"] = x_sample_noquant log["sample_diff"] = torch.abs(x_sample_noquant - x_sample) - except: + except Exception: pass log["sample"] = x_sample diff --git a/extensions-builtin/LDSR/scripts/ldsr_model.py b/extensions-builtin/LDSR/scripts/ldsr_model.py index da19cff1..fbbe9005 100644 --- a/extensions-builtin/LDSR/scripts/ldsr_model.py +++ b/extensions-builtin/LDSR/scripts/ldsr_model.py @@ -7,7 +7,8 @@ from basicsr.utils.download_util import load_file_from_url from modules.upscaler import Upscaler, UpscalerData from ldsr_model_arch import LDSR from modules import shared, script_callbacks -import sd_hijack_autoencoder, sd_hijack_ddpm_v1 +import sd_hijack_autoencoder # noqa: F401 +import sd_hijack_ddpm_v1 # noqa: F401 class UpscalerLDSR(Upscaler): diff --git a/extensions-builtin/LDSR/sd_hijack_autoencoder.py b/extensions-builtin/LDSR/sd_hijack_autoencoder.py index 8e03c7f8..6303fed5 100644 --- a/extensions-builtin/LDSR/sd_hijack_autoencoder.py +++ b/extensions-builtin/LDSR/sd_hijack_autoencoder.py @@ -1,16 +1,21 @@ # The content of this file comes from the ldm/models/autoencoder.py file of the compvis/stable-diffusion repo # The VQModel & VQModelInterface were subsequently removed from ldm/models/autoencoder.py when we moved to the stability-ai/stablediffusion repo # As the LDSR upscaler relies on VQModel & VQModelInterface, the hijack aims to put them back into the ldm.models.autoencoder - +import numpy as np import torch import pytorch_lightning as pl import torch.nn.functional as F from contextlib import contextmanager + +from torch.optim.lr_scheduler import LambdaLR + +from ldm.modules.ema import LitEma from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer from ldm.modules.diffusionmodules.model import Encoder, Decoder from ldm.util import instantiate_from_config import ldm.models.autoencoder +from packaging import version class VQModel(pl.LightningModule): def __init__(self, @@ -165,7 +170,7 @@ class VQModel(pl.LightningModule): def validation_step(self, batch, batch_idx): log_dict = self._validation_step(batch, batch_idx) with self.ema_scope(): - log_dict_ema = self._validation_step(batch, batch_idx, suffix="_ema") + self._validation_step(batch, batch_idx, suffix="_ema") return log_dict def _validation_step(self, batch, batch_idx, suffix=""): @@ -249,7 +254,8 @@ class VQModel(pl.LightningModule): if plot_ema: with self.ema_scope(): xrec_ema, _ = self(x) - if x.shape[1] > 3: xrec_ema = self.to_rgb(xrec_ema) + if x.shape[1] > 3: + xrec_ema = self.to_rgb(xrec_ema) log["reconstructions_ema"] = xrec_ema return log diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py index 5c0488e5..4d3f6c56 100644 --- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py +++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py @@ -450,7 +450,7 @@ class LatentDiffusionV1(DDPMV1): self.cond_stage_key = cond_stage_key try: self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1 - except: + except Exception: self.num_downs = 0 if not scale_by_std: self.scale_factor = scale_factor @@ -877,16 +877,6 @@ class LatentDiffusionV1(DDPMV1): c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float())) return self.p_losses(x, c, t, *args, **kwargs) - def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset - def rescale_bbox(bbox): - x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2]) - y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3]) - w = min(bbox[2] / crop_coordinates[2], 1 - x0) - h = min(bbox[3] / crop_coordinates[3], 1 - y0) - return x0, y0, w, h - - return [rescale_bbox(b) for b in bboxes] - def apply_model(self, x_noisy, t, cond, return_ids=False): if isinstance(cond, dict): @@ -1157,8 +1147,10 @@ class LatentDiffusionV1(DDPMV1): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(x0_partial) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) return img, intermediates @torch.no_grad() @@ -1205,8 +1197,10 @@ class LatentDiffusionV1(DDPMV1): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(img) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) if return_intermediates: return img, intermediates @@ -1322,7 +1316,7 @@ class LatentDiffusionV1(DDPMV1): if inpaint: # make a simple center square - b, h, w = z.shape[0], z.shape[2], z.shape[3] + h, w = z.shape[2], z.shape[3] mask = torch.ones(N, h, w).to(self.device) # zeros will be filled in mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0. diff --git a/extensions-builtin/Lora/lora.py b/extensions-builtin/Lora/lora.py index ba1293df..0ab43229 100644 --- a/extensions-builtin/Lora/lora.py +++ b/extensions-builtin/Lora/lora.py @@ -1,4 +1,3 @@ -import glob
import os
import re
import torch
diff --git a/extensions-builtin/ScuNET/scripts/scunet_model.py b/extensions-builtin/ScuNET/scripts/scunet_model.py index c7fd5739..aa2fdb3a 100644 --- a/extensions-builtin/ScuNET/scripts/scunet_model.py +++ b/extensions-builtin/ScuNET/scripts/scunet_model.py @@ -13,7 +13,6 @@ import modules.upscaler from modules import devices, modelloader from scunet_model_arch import SCUNet as net from modules.shared import opts -from modules import images class UpscalerScuNET(modules.upscaler.Upscaler): diff --git a/extensions-builtin/ScuNET/scunet_model_arch.py b/extensions-builtin/ScuNET/scunet_model_arch.py index 43ca8d36..8028918a 100644 --- a/extensions-builtin/ScuNET/scunet_model_arch.py +++ b/extensions-builtin/ScuNET/scunet_model_arch.py @@ -61,7 +61,9 @@ class WMSA(nn.Module): Returns: output: tensor shape [b h w c] """ - if self.type != 'W': x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2)) + if self.type != 'W': + x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2)) + x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size) h_windows = x.size(1) w_windows = x.size(2) @@ -85,8 +87,9 @@ class WMSA(nn.Module): output = self.linear(output) output = rearrange(output, 'b (w1 w2) (p1 p2) c -> b (w1 p1) (w2 p2) c', w1=h_windows, p1=self.window_size) - if self.type != 'W': output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), - dims=(1, 2)) + if self.type != 'W': + output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), dims=(1, 2)) + return output def relative_embedding(self): diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py index e8783bca..55dd94ab 100644 --- a/extensions-builtin/SwinIR/scripts/swinir_model.py +++ b/extensions-builtin/SwinIR/scripts/swinir_model.py @@ -1,4 +1,3 @@ -import contextlib import os import numpy as np @@ -8,7 +7,7 @@ from basicsr.utils.download_util import load_file_from_url from tqdm import tqdm from modules import modelloader, devices, script_callbacks, shared -from modules.shared import cmd_opts, opts, state +from modules.shared import opts, state from swinir_model_arch import SwinIR as net from swinir_model_arch_v2 import Swin2SR as net2 |