Checklist
- [x] The issue exists after disabling all extensions
- [x] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
- [x] The issue exists in the current version of the webui
- [x] The issue has not been reported before recently
- [ ] The issue has been reported before but has not been fixed yet
What happened?
When generating SDXL images with Hires. fix on an Intel Arc A770 (DirectML) GPU, the generation frequently stops mid-process, usually at the Hires. fix stage (around 50-70% progress). This happens even with --lowvram and --no-half-vae enabled, and at relatively low base resolutions like 512x512. The VRAM usage shown by Task Manager often indicates around 3GB used when it stops, while the console shows Out Of Memory (OOM) errors (e.g., "Could not allocate tensor...") or sometimes a NaN error with automatic 32-bit VAE retry. The issue is inconsistent; sometimes a generation succeeds, but subsequent attempts often fail.
Steps to reproduce the problem
- Hardware: Intel Arc A770 16GB VRAM, Windows 11.
- Web UI Setup:
- Using Automatic1111 stable-diffusion-webui (latest
git pull).
webui-user.bat includes: --autolaunch --precision full --skip-torch-cuda-test --opt-sdp-attention --use-directml --lowvram --no-half-vae- Python 3.10.9, Torch 2.0.0+cpu (as shown in startup log, despite
--reinstall-torch attempts).
- Model: Use an SDXL 1.0 base model (e.g.,
novaOrangeXL_reV10.safetensors or waiNSFWIllustrious_v140.safetensors).
- Steps:
a. Launch Web UI using
webui-user.bat.
b. Go to the txt2img tab.
c. Enter a simple prompt (e.g., "masterpiece, best quality, beautiful girl, clear eyes").
d. Set image dimensions to Width: 512, Height: 512.
e. Enable Hires. fix.
f. Set Upscale by: 2.
g. Set Hires steps: 24 (or similar, default often used).
h. Set Denoising strength: 0.7 (or similar).
i. Set Sampler: Euler a (or any other, issue persists).
j. Click "Generate".
- Observe: The generation often stops at around 50-70% progress (Hires. fix stage). The console shows
RuntimeError: Could not allocate tensor... or sometimes prints "A tensor with all NaNs was produced in VAE." before converting to float32 and then potentially still failing with OOM.
- Inconsistency: If the first generation succeeds, attempting a second generation immediately after often results in a failure with the same errors. Restarting the Web UI process (closing and relaunching
webui-user.bat) usually allows for one successful generation again.
What should have happened?
The image generation, including the Hires. fix stage, should complete successfully without encountering Out Of Memory errors or NaN issues. The process should be stable, allowing for continuous image generation without requiring a Web UI restart after each successful image. Given the 16GB VRAM on the Intel Arc A770, it should be capable of consistently handling SDXL Hires. fix up to 1024x1024 (or at least 896x896) without crashing or inconsistent behavior, especially with --lowvram and --no-half-vae enabled.
What browsers do you use to access the UI ?
Microsoft Edge
Sysinfo
{
"Platform": "Windows-10-10.0.26100-SP0",
"Python": "3.10.9",
"Version": "v1.10.1-amd-39-g6d85a7df",
"Commit": "6d85a7dfa4977ae4eece9cbbab4725123833be14",
"Git status": "On branch master\nYour branch is up to date with 'origin/master'.\n\nChanges not staged for commit:\n (use "git add ..." to update what will be committed)\n (use "git restore ..." to discard changes in working directory)\n\tmodified: launch.py\n\tmodified: webui-user.bat\n\nno changes added to commit (use "git add" and/or "git commit -a")",
"Script path": "D:\sd_directml",
"Data path": "D:\sd_directml",
"Extensions dir": "D:\sd_directml\extensions",
"Checksum": "ba7a852b3fbd4f24b5aad10e0a0c032445127e2e79154b9925ee223e4c5c4b70",
"Commandline": [
"launch.py",
"--autolaunch",
"--precision",
"full",
"--skip-torch-cuda-test",
"--opt-sdp-attention",
"--use-directml",
"--lowvram",
"--no-half-vae",
"--autolaunch",
"--precision",
"full",
"--skip-torch-cuda-test",
"--opt-sdp-attention",
"--use-directml",
"--lowvram",
"--no-half-vae",
"--autolaunch",
"--precision",
"full",
"--skip-torch-cuda-test",
"--opt-sdp-attention",
"--use-directml",
"--lowvram",
"--no-half-vae"
],
"Torch env info": {
"torch_version": "2.0.0+cpu",
"is_debug_build": "False",
"cuda_compiled_version": null,
"gcc_version": null,
"clang_version": null,
"cmake_version": null,
"os": "Microsoft Windows 11 Home",
"libc_version": "N/A",
"python_version": "3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)] (64-bit runtime)",
"python_platform": "Windows-10-10.0.26100-SP0",
"is_cuda_available": "False",
"cuda_runtime_version": null,
"cuda_module_loading": "N/A",
"nvidia_driver_version": null,
"nvidia_gpu_models": null,
"cudnn_version": null,
"pip_version": "pip3",
"pip_packages": [
"numpy==1.26.4",
"open-clip-torch==2.20.0",
"pytorch-lightning==1.9.4",
"torch==2.0.0",
"torch-directml==0.2.0.dev230426",
"torchdiffeq==0.2.3",
"torchmetrics==1.7.4",
"torchsde==0.2.6",
"torchvision==0.15.1"
],
"conda_packages": null,
"hip_compiled_version": "N/A",
"hip_runtime_version": "N/A",
"miopen_runtime_version": "N/A",
"caching_allocator_config": "",
"is_xnnpack_available": "True",
"cpu_info": [
"Architecture=9",
"CurrentClockSpeed=2592",
"DeviceID=CPU0",
"Family=205",
"L2CacheSize=3072",
"L2CacheSpeed=",
"Manufacturer=GenuineIntel",
"MaxClockSpeed=2592",
"Name=11th Gen Intel(R) Core(TM) i5-11400 @ 2.60GHz",
"ProcessorType=3",
"Revision="
]
},
"Exceptions": [
{
"exception": "",
"traceback": [
[
"D:\sd_directml\modules\call_queue.py, line 74, f",
"res = list(func(*args, **kwargs))"
],
[
"D:\sd_directml\modules\call_queue.py, line 53, f",
"res = func(*args, **kwargs)"
],
[
"D:\sd_directml\modules\call_queue.py, line 37, f",
"res = func(*args, **kwargs)"
],
[
"D:\sd_directml\modules\txt2img.py, line 109, txt2img",
"processed = processing.process_images(p)"
],
[
"D:\sd_directml\modules\processing.py, line 849, process_images",
"res = process_images_inner(p)"
],
[
"D:\sd_directml\extensions\sd-webui-controlnet\scripts\batch_hijack.py, line 59, processing_process_images_hijack",
"return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)"
],
[
"D:\sd_directml\modules\processing.py, line 1083, process_images_inner",
"samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)"
],
[
"D:\sd_directml\modules\processing.py, line 1457, sample",
"return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)"
],
[
"D:\sd_directml\modules\processing.py, line 1549, sample_hr_pass",
"samples = self.sampler.sample_img2img(self, samples, noise, self.hr_c, self.hr_uc, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)"
],
[
"D:\sd_directml\modules\sd_samplers_kdiffusion.py, line 187, sample_img2img",
"samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))"
],
[
"D:\sd_directml\modules\sd_samplers_common.py, line 272, launch_sampling",
"return func()"
],
[
"D:\sd_directml\modules\sd_samplers_kdiffusion.py, line 187, ",
"samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))"
],
[
"D:\sd_directml\venv\lib\site-packages\torch\utils\contextlib.py, line 115, decorate_context",
"return func(*args, **kwargs)"
],
[
"D:\sd_directml\repositories\k-diffusion\k_diffusion\sampling.py, line 145, sample_euler_ancestral",
"denoised = model(x, sigmas[i] * s_in, **extra_args)"
],
[
"D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py, line 1501, call_impl",
"return forward_call(*args, **kwargs)"
],
[
"D:\sd_directml\modules\sd_samplers_cfg_denoiser.py, line 268, forward",
"x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(c_crossattn, image_cond_in[a:b]))"
],
[
"D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py, line 1501, call_impl",
"return forward_call(*args, **kwargs)"
],
[
"D:\sd_directml\repositories\k-diffusion\k_diffusion\external.py, line 112, forward",
"eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)"
],
[
"D:\sd_directml\repositories\k-diffusion\k_diffusion\external.py, line 138, get_eps",
"return self.inner_model.apply_model(*args, **kwargs)"
],
[
"D:\sd_directml\modules\sd_models_xl.py, line 43, apply_model",
"return self.model(x, t, cond)"
],
[
"D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py, line 1501, call_impl",
"return forward_call(*args, **kwargs)"
],
[
"D:\sd_directml\modules\sd_hijack_utils.py, line 22, ",
"setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))"
],
[
"D:\sd_directml\modules\sd_hijack_utils.py, line 34, call",
"return self.__sub_func(self.__orig_func, *args, **kwargs)"
],
[
"D:\sd_directml\modules\sd_hijack_unet.py, line 50, apply_model",
"result = orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs)"
],
[
"D:\sd_directml\repositories\generative-models\sgm\modules\diffusionmodules\wrappers.py, line 28, forward",
"return self.diffusion_model("
],
[
"D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py, line 1501, call_impl",
"return forward_call(*args, **kwargs)"
],
[
"D:\sd_directml\modules\sd_unet.py, line 91, UNetModel_forward",
"return original_forward(self, x, timesteps, context, *args, **kwargs)"
],
[
"D:\sd_directml\repositories\generative-models\sgm\modules\diffusionmodules\openaimodel.py, line 993, forward",
"h = module(h, emb, context)"
],
[
"D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py, line 1538, call_impl",
"result = forward_call(*args, **kwargs)"
],
[
"D:\sd_directml\repositories\generative-models\sgm\modules\diffusionmodules\openaimodel.py, line 100, forward",
"x = layer(x, context)"
],
[
"D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py, line 1501, call_impl",
"return forward_call(*args, **kwargs)"
],
[
"D:\sd_directml\repositories\generative-models\sgm\modules\attention.py, line 627, forward",
"x = block(x, context=context[i])"
],
[
"D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py, line 1501, call_impl",
"return forward_call(*args, **kwargs)"
],
[
"D:\sd_directml\repositories\generative-models\sgm\modules\attention.py, line 459, forward",
"return checkpoint("
],
[
"D:\sd_directml\repositories\generative-models\sgm\modules\diffusionmodules\util.py, line 167, checkpoint",
"return func(*inputs)"
],
[
"D:\sd_directml\repositories\generative-models\sgm\modules\attention.py, line 467, forward",
"self.attn1("
],
[
"D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py, line 1501, call_impl",
"return forward_call(args, **kwargs)"
],
[
"D:\sd_directml\modules\sd_hijack_optimizations.py, line 547, scaled_dot_product_attention_forward",
"hidden_states = torch.nn.functional.scaled_dot_product_attention("
]
]
}
],
"CPU": {
"model": "Intel64 Family 6 Model 167 Stepping 1, GenuineIntel",
"count logical": 12,
"count physical": 6
},
"RAM": {
"total": "16GB",
"used": "10GB",
"free": "6GB"
},
"Extensions": [
{
"name": "sd-webui-animatediff",
"path": "D:\sd_directml\extensions\sd-webui-animatediff",
"commit": "a88e88912bcbae0531caccfc50fd639f6ea83fd0",
"branch": "master",
"remote": "https://github.com/continue-revolution/sd-webui-animatediff"
},
{
"name": "sd-webui-controlnet",
"path": "D:\sd_directml\extensions\sd-webui-controlnet",
"commit": "56cec5b2958edf3b1807b7e7b2b1b5186dbd2f81",
"branch": "main",
"remote": "https://github.com/Mikubill/sd-webui-controlnet"
},
{
"name": "stable-diffusion-webui-wd14-tagger",
"path": "D:\sd_directml\extensions\stable-diffusion-webui-wd14-tagger",
"commit": "e72d984bdbed832ba83e2a443238c3851b9088ae",
"branch": "master",
"remote": "http://github.com/picobyte/stable-diffusion-webui-wd14-tagger.git"
}
],
"Inactive extensions": [],
"Environment": {
"COMMANDLINE_ARGS": "--autolaunch --precision full --skip-torch-cuda-test --opt-sdp-attention --use-directml --lowvram --no-half-vae",
"GRADIO_ANALYTICS_ENABLED": "False"
},
"Config": {
"ldsr_steps": 100,
"ldsr_cached": false,
"SCUNET_tile": 256,
"SCUNET_tile_overlap": 8,
"SWIN_tile": 192,
"SWIN_tile_overlap": 8,
"SWIN_torch_compile": false,
"hypertile_enable_unet": false,
"hypertile_enable_unet_secondpass": false,
"hypertile_max_depth_unet": 3,
"hypertile_max_tile_unet": 256,
"hypertile_swap_size_unet": 3,
"hypertile_enable_vae": false,
"hypertile_max_depth_vae": 3,
"hypertile_max_tile_vae": 128,
"hypertile_swap_size_vae": 3,
"sd_model_checkpoint": "novaOrangeXL_reV10.safetensors [2e13269995]",
"sd_checkpoint_hash": "2e13269995e4c3e1e1edb7d45e815dc311f770558ee5a31f248807f5d598e964",
"outdir_samples": "",
"outdir_txt2img_samples": "outputs\txt2img-images",
"outdir_img2img_samples": "outputs\img2img-images",
"outdir_extras_samples": "outputs\extras-images",
"outdir_grids": "",
"outdir_txt2img_grids": "outputs\txt2img-grids",
"outdir_img2img_grids": "outputs\img2img-grids",
"outdir_save": "log\images",
"outdir_init_images": "outputs\init-images",
"onnx_cached_models_path": "D:\sd_directml\models\ONNX\cache",
"onnx_temp_dir": "D:\sd_directml\models\ONNX\temp",
"samples_save": true,
"samples_format": "png",
"samples_filename_pattern": "",
"save_images_add_number": true,
"save_images_replace_action": "Replace",
"grid_save": true,
"grid_format": "png",
"grid_extended_filename": false,
"grid_only_if_multiple": true,
"grid_prevent_empty_spots": false,
"grid_zip_filename_pattern": "",
"n_rows": -1,
"font": "",
"grid_text_active_color": "#000000",
"grid_text_inactive_color": "#999999",
"grid_background_color": "#ffffff",
"save_images_before_face_restoration": false,
"save_images_before_highres_fix": false,
"save_images_before_color_correction": false,
"save_mask": false,
"save_mask_composite": false,
"jpeg_quality": 80,
"webp_lossless": false,
"export_for_4chan": true,
"img_downscale_threshold": 4.0,
"target_side_length": 4000.0,
"img_max_size_mp": 200.0,
"use_original_name_batch": true,
"use_upscaler_name_as_suffix": false,
"save_selected_only": true,
"save_write_log_csv": true,
"save_init_img": false,
"temp_dir": "",
"clean_temp_dir_at_start": false,
"save_incomplete_images": false,
"notification_audio": true,
"notification_volume": 100,
"save_to_dirs": true,
"grid_save_to_dirs": true,
"use_save_to_dirs_for_ui": false,
"directories_filename_pattern": "[date]",
"directories_max_prompt_words": 8,
"auto_backcompat": true,
"use_old_emphasis_implementation": false,
"use_old_karras_scheduler_sigmas": false,
"no_dpmpp_sde_batch_determinism": false,
"use_old_hires_fix_width_height": false,
"hires_fix_use_firstpass_conds": false,
"use_old_scheduling": false,
"use_downcasted_alpha_bar": false,
"refiner_switch_by_sample_steps": false,
"lora_functional": false,
"extra_networks_show_hidden_directories": true,
"extra_networks_dir_button_function": false,
"extra_networks_hidden_models": "When searched",
"extra_networks_default_multiplier": 1,
"extra_networks_card_width": 0.0,
"extra_networks_card_height": 0.0,
"extra_networks_card_text_scale": 1,
"extra_networks_card_show_desc": true,
"extra_networks_card_description_is_html": false,
"extra_networks_card_order_field": "Path",
"extra_networks_card_order": "Ascending",
"extra_networks_tree_view_style": "Dirs",
"extra_networks_tree_view_default_enabled": true,
"extra_networks_tree_view_default_width": 180.0,
"extra_networks_add_text_separator": " ",
"ui_extra_networks_tab_reorder": "",
"textual_inversion_print_at_load": false,
"textual_inversion_add_hashes_to_infotext": true,
"sd_hypernetwork": "None",
"sd_lora": "None",
"lora_preferred_name": "Alias from file",
"lora_add_hashes_to_infotext": true,
"lora_bundled_ti_to_infotext": true,
"lora_show_all": false,
"lora_hide_unknown_for_versions": [],
"lora_in_memory_limit": 0,
"lora_not_found_warning_console": false,
"lora_not_found_gradio_warning": false,
"onnx_enable": false,
"diffusers_pipeline": "ONNX Stable Diffusion",
"diffusers_vae_upcast": "default",
"onnx_execution_provider": "CUDAExecutionProvider",
"onnx_cache_converted": true,
"olive_enable": false,
"olive_submodels": [],
"olive_float16": true,
"olive_vae_encoder_float32": false,
"olive_static_dims": true,
"olive_cache_optimized": true,
"cross_attention_optimization": "Automatic",
"s_min_uncond": 0,
"s_min_uncond_all": false,
"token_merging_ratio": 0,
"token_merging_ratio_img2img": 0,
"token_merging_ratio_hr": 0,
"pad_cond_uncond": false,
"pad_cond_uncond_v0": false,
"persistent_cond_cache": true,
"batch_cond_uncond": true,
"fp8_storage": "Disable",
"cache_fp16_weight": false,
"directml_memory_provider": "Performance Counter",
"hide_samplers": [],
"eta_ddim": 0,
"eta_ancestral": 1,
"ddim_discretize": "uniform",
"s_churn": 0,
"s_tmin": 0,
"s_tmax": 0,
"s_noise": 1,
"sigma_min": 0.0,
"sigma_max": 0.0,
"rho": 0.0,
"eta_noise_seed_delta": 0,
"always_discard_next_to_last_sigma": false,
"sgm_noise_multiplier": false,
"uni_pc_variant": "bh1",
"uni_pc_skip_type": "time_uniform",
"uni_pc_order": 3,
"uni_pc_lower_order_final": true,
"sd_noise_schedule": "Default",
"skip_early_cond": 0,
"beta_dist_alpha": 0.6,
"beta_dist_beta": 0.6,
"sd_checkpoints_limit": 1,
"sd_checkpoints_keep_in_cpu": true,
"sd_checkpoint_cache": 0,
"sd_unet": "Automatic",
"enable_quantization": false,
"emphasis": "Original",
"enable_batch_seeds": true,
"comma_padding_backtrack": 20,
"sdxl_clip_l_skip": false,
"CLIP_stop_at_last_layers": 2,
"upcast_attn": false,
"randn_source": "GPU",
"tiling": false,
"hires_fix_refiner_pass": "second pass",
"enable_prompt_comments": true,
"sd3_enable_t5": false,
"sdxl_crop_top": 0.0,
"sdxl_crop_left": 0.0,
"sdxl_refiner_low_aesthetic_score": 2.5,
"sdxl_refiner_high_aesthetic_score": 6.0,
"sd_vae_checkpoint_cache": 0,
"sd_vae": "sdxlVAE_sdxlVAE.safetensors",
"sd_vae_overrides_per_model_preferences": true,
"auto_vae_precision_bfloat16": false,
"auto_vae_precision": true,
"sd_vae_encode_method": "Full",
"sd_vae_decode_method": "Full",
"inpainting_mask_weight": 1,
"initial_noise_multiplier": 1,
"img2img_extra_noise": 0,
"img2img_color_correction": false,
"img2img_fix_steps": false,
"img2img_background_color": "#ffffff",
"img2img_editor_height": 720,
"img2img_sketch_default_brush_color": "#ffffff",
"img2img_inpaint_mask_brush_color": "#ffffff",
"img2img_inpaint_sketch_default_brush_color": "#ffffff",
"return_mask": false,
"return_mask_composite": false,
"img2img_batch_show_results_limit": 32,
"overlay_inpaint": true,
"return_grid": true,
"do_not_show_images": false,
"js_modal_lightbox": true,
"js_modal_lightbox_initially_zoomed": true,
"js_modal_lightbox_gamepad": false,
"js_modal_lightbox_gamepad_repeat": 250.0,
"sd_webui_modal_lightbox_icon_opacity": 1,
"sd_webui_modal_lightbox_toolbar_opacity": 0.9,
"gallery_height": "",
"open_dir_button_choice": "Subdirectory",
"enable_pnginfo": true,
"save_txt": false,
"add_model_name_to_info": true,
"add_model_hash_to_info": true,
"add_vae_name_to_info": true,
"add_vae_hash_to_info": true,
"add_user_name_to_info": false,
"add_version_to_infotext": true,
"disable_weights_auto_swap": true,
"infotext_skip_pasting": [],
"infotext_styles": "Apply if any",
"show_progressbar": true,
"live_previews_enable": true,
"live_previews_image_format": "png",
"show_progress_grid": true,
"show_progress_every_n_steps": 10,
"show_progress_type": "Approx NN",
"live_preview_allow_lowvram_full": false,
"live_preview_content": "Prompt",
"live_preview_refresh_period": 1000.0,
"live_preview_fast_interrupt": false,
"js_live_preview_in_modal_lightbox": false,
"prevent_screen_sleep_during_generation": true,
"keyedit_precision_attention": 0.1,
"keyedit_precision_extra": 0.05,
"keyedit_delimiters": ".,\/!?%^;:{}=`~() ",
"keyedit_delimiters_whitespace": [
"Tab",
"Carriage Return",
"Line Feed"
],
"keyedit_move": true,
"disable_token_counters": false,
"include_styles_into_token_counters": true,
"extra_options_txt2img": [],
"extra_options_img2img": [],
"extra_options_cols": 1,
"extra_options_accordion": false,
"compact_prompt_box": false,
"samplers_in_dropdown": true,
"dimensions_and_batch_together": true,
"sd_checkpoint_dropdown_use_short": false,
"hires_fix_show_sampler": false,
"hires_fix_show_prompts": false,
"txt2img_settings_accordion": false,
"img2img_settings_accordion": false,
"interrupt_after_current": true,
"localization": "None",
"quicksettings_list": [
"sd_model_checkpoint",
"CLIP_stop_at_last_layers"
],
"ui_tab_order": [],
"hidden_tabs": [],
"ui_reorder_list": [],
"gradio_theme": "Default",
"gradio_themes_cache": true,
"show_progress_in_title": true,
"send_seed": true,
"send_size": true,
"enable_reloading_ui_scripts": false,
"api_enable_requests": true,
"api_forbid_local_requests": true,
"api_useragent": "",
"prioritized_callbacks_app_started": [],
"prioritized_callbacks_model_loaded": [],
"prioritized_callbacks_ui_settings": [],
"prioritized_callbacks_infotext_pasted": [],
"prioritized_callbacks_script_unloaded": [],
"prioritized_callbacks_before_ui": [],
"prioritized_callbacks_list_optimizers": [],
"prioritized_callbacks_before_token_counter": [],
"prioritized_callbacks_script_before_process": [],
"prioritized_callbacks_script_process": [],
"prioritized_callbacks_script_post_sample": [],
"prioritized_callbacks_script_on_mask_blend": [],
"prioritized_callbacks_script_postprocess_maskoverlay": [],
"profiling_enable": false,
"profiling_activities": [
"CPU"
],
"profiling_record_shapes": true,
"profiling_profile_memory": true,
"profiling_with_stack": true,
"profiling_filename": "trace.json",
"auto_launch_browser": "Local",
"enable_console_prompts": false,
"show_warnings": false,
"show_gradio_deprecation_warnings": true,
"memmon_poll_rate": 8,
"samples_log_stdout": false,
"multiple_tqdm": true,
"enable_upscale_progressbar": true,
"print_hypernet_extra": false,
"list_hidden_files": true,
"disable_mmap_load_safetensors": false,
"hide_ldm_prints": true,
"dump_stacks_on_signal": false,
"face_restoration": false,
"face_restoration_model": "CodeFormer",
"code_former_weight": 0.5,
"face_restoration_unload": false,
"postprocessing_enable_in_main_ui": [],
"postprocessing_disable_in_extras": [],
"postprocessing_operation_order": [],
"upscaling_max_images_in_cache": 5,
"postprocessing_existing_caption_action": "Ignore",
"ESRGAN_tile": 192,
"ESRGAN_tile_overlap": 8,
"realesrgan_enabled_models": [
"R-ESRGAN 4x+",
"R-ESRGAN 4x+ Anime6B"
],
"dat_enabled_models": [
"DAT x2",
"DAT x3",
"DAT x4"
],
"DAT_tile": 192,
"DAT_tile_overlap": 8,
"set_scale_by_when_changing_upscaler": false,
"unload_models_when_training": false,
"pin_memory": false,
"save_optimizer_state": false,
"save_training_settings_to_txt": true,
"dataset_filename_word_regex": "",
"dataset_filename_join_string": " ",
"training_image_repeats_per_epoch": 1,
"training_write_csv_every": 500.0,
"training_xattention_optimizations": false,
"training_enable_tensorboard": false,
"training_tensorboard_save_images": false,
"training_tensorboard_flush_every": 120.0,
"canvas_hotkey_zoom": "Alt",
"canvas_hotkey_adjust": "Ctrl",
"canvas_hotkey_shrink_brush": "Q",
"canvas_hotkey_grow_brush": "W",
"canvas_hotkey_move": "F",
"canvas_hotkey_fullscreen": "S",
"canvas_hotkey_reset": "R",
"canvas_hotkey_overlap": "O",
"canvas_show_tooltip": true,
"canvas_auto_expand": true,
"canvas_blur_prompt": false,
"canvas_disabled_functions": [
"Overlap"
],
"interrogate_keep_models_in_memory": false,
"interrogate_return_ranks": false,
"interrogate_clip_num_beams": 1,
"interrogate_clip_min_length": 24,
"interrogate_clip_max_length": 48,
"interrogate_clip_dict_limit": 1500.0,
"interrogate_clip_skip_categories": [],
"interrogate_deepbooru_score_threshold": 0.5,
"deepbooru_sort_alpha": true,
"deepbooru_use_spaces": true,
"deepbooru_escape": true,
"deepbooru_filter_tags": "",
"disabled_extensions": [],
"disable_all_extensions": "none",
"animatediff_model_path": "",
"animatediff_default_save_formats": [
"GIF",
"PNG"
],
"animatediff_save_to_custom": true,
"animatediff_frame_extract_path": "",
"animatediff_frame_extract_remove": false,
"animatediff_default_frame_extract_method": "ffmpeg",
"animatediff_optimize_gif_palette": false,
"animatediff_optimize_gif_gifsicle": false,
"animatediff_mp4_crf": 23,
"animatediff_mp4_preset": "",
"animatediff_mp4_tune": "",
"animatediff_webp_quality": 80,
"animatediff_webp_lossless": false,
"animatediff_s3_enable": false,
"animatediff_s3_host": "",
"animatediff_s3_port": "",
"animatediff_s3_access_key": "",
"animatediff_s3_secret_key": "",
"animatediff_s3_storge_bucket": "",
"control_net_detectedmap_dir": "detected_maps",
"control_net_models_path": "",
"control_net_modules_path": "",
"control_net_unit_count": 3,
"control_net_model_cache_size": 2,
"control_net_inpaint_blur_sigma": 7,
"control_net_no_detectmap": false,
"control_net_detectmap_autosaving": false,
"control_net_allow_script_control": false,
"control_net_sync_field_args": true,
"controlnet_show_batch_images_in_ui": false,
"controlnet_increment_seed_during_batch": false,
"controlnet_disable_openpose_edit": false,
"controlnet_disable_photopea_edit": false,
"controlnet_photopea_warning": true,
"controlnet_ignore_noninpaint_mask": false,
"controlnet_clip_detector_on_cpu": false,
"controlnet_control_type_dropdown": false,
"tagger_out_filename_fmt": "[name].[output_extension]",
"tagger_count_threshold": 100.0,
"tagger_batch_recursive": true,
"tagger_auto_serde_json": true,
"tagger_store_images": false,
"tagger_weighted_tags_files": false,
"tagger_verbose": false,
"tagger_repl_us": true,
"tagger_repl_us_excl": "0_0, (o)(o), ++, +-, .., , <|><|>, ==, ><, 3_3, 6_9, >o, @@, ^^, o_o, u_u, x_x, ||, ||_||",
"tagger_escape": false,
"tagger_batch_size": 1024,
"tagger_hf_cache_dir": "D:\sd_directml\models\interrogators",
"prioritized_callbacks_ui_tabs": [],
"prioritized_callbacks_cfg_denoiser": [],
"prioritized_callbacks_after_component": [],
"prioritized_callbacks_on_reload": [],
"prioritized_callbacks_script_before_process_batch": [],
"prioritized_callbacks_script_postprocess": [],
"prioritized_callbacks_script_postprocess_batch": [],
"prioritized_callbacks_script_postprocess_batch_list": [],
"prioritized_callbacks_script_postprocess_image": []
},
"Startup": {
"total": 117.79217195510864,
"records": {
"launcher": 35.03606104850769,
"import torch": 21.190768241882324,
"import gradio": 1.6846561431884766,
"setup paths": 12.206217765808105,
"import ldm": 0.007937192916870117,
"import sgm": 0.0,
"initialize shared": 2.566276788711548,
"other imports": 0.046120643615722656,
"opts onchange": 0.0010085105895996094,
"setup SD model": 0.0,
"setup codeformer": 0.002558469772338867,
"setup gfpgan": 0.0189664363861084,
"set samplers": 0.00102996826171875,
"list extensions": 0.0015044212341308594,
"restore config state file": 0.0,
"list SD models": 0.07561135292053223,
"list localizations": 0.0,
"load scripts/custom_code.py": 0.013432025909423828,
"load scripts/img2imgalt.py": 0.0015058517456054688,
"load scripts/loopback.py": 0.0,
"load scripts/outpainting_mk_2.py": 0.0010120868682861328,
"load scripts/poor_mans_outpainting.py": 0.0009992122650146484,
"load scripts/postprocessing_codeformer.py": 0.0,
"load scripts/postprocessing_gfpgan.py": 0.0010037422180175781,
"load scripts/postprocessing_upscale.py": 0.0,
"load scripts/prompt_matrix.py": 0.0017118453979492188,
"load scripts/prompts_from_file.py": 0.0011334419250488281,
"load scripts/sd_upscale.py": 0.0010564327239990234,
"load scripts/xyz_grid.py": 0.001165151596069336,
"load scripts/ldsr_model.py": 1.1645009517669678,
"load scripts/lora_script.py": 0.2477409839630127,
"load scripts/scunet_model.py": 0.041359901428222656,
"load scripts/swinir_model.py": 0.040180206298828125,
"load scripts/hotkey_config.py": 0.0017354488372802734,
"load scripts/extra_options_section.py": 0.0014653205871582031,
"load scripts/hypertile_script.py": 0.08105015754699707,
"load scripts/postprocessing_autosized_crop.py": 0.0012936592102050781,
"load scripts/postprocessing_caption.py": 0.0,
"load scripts/postprocessing_create_flipped_copies.py": 0.0015063285827636719,
"load scripts/postprocessing_focal_crop.py": 0.002042531967163086,
"load scripts/postprocessing_split_oversized.py": 0.0009915828704833984,
"load scripts/soft_inpainting.py": 0.0,
"load scripts/animatediff.py": 0.19388294219970703,
"load scripts/animatediff_freeinit.py": 0.0010075569152832031,
"load scripts/animatediff_i2ibatch.py": 0.0010106563568115234,
"load scripts/animatediff_infotext.py": 0.0,
"load scripts/animatediff_infv2v.py": 0.0011479854583740234,
"load scripts/animatediff_latent.py": 0.0,
"load scripts/animatediff_logger.py": 0.0012199878692626953,
"load scripts/animatediff_mm.py": 0.0,
"load scripts/animatediff_output.py": 0.0,
"load scripts/animatediff_prompt.py": 0.0015058517456054688,
"load scripts/animatediff_settings.py": 0.0,
"load scripts/animatediff_ui.py": 0.0,
"load scripts/animatediff_utils.py": 0.0015609264373779297,
"load scripts/animatediff_xyz.py": 0.0,
"load scripts/adapter.py": 0.002076864242553711,
"load scripts/api.py": 0.3266606330871582,
"load scripts/batch_hijack.py": 0.0015680789947509766,
"load scripts/cldm.py": 0.0026121139526367188,
"load scripts/controlnet.py": 1.2729477882385254,
"load scripts/controlnet_diffusers.py": 0.0010955333709716797,
"load scripts/controlnet_lllite.py": 0.0,
"load scripts/controlnet_lora.py": 0.0,
"load scripts/controlnet_model_guess.py": 0.0015072822570800781,
"load scripts/controlnet_sparsectrl.py": 0.0,
"load scripts/controlnet_version.py": 0.0,
"load scripts/enums.py": 0.0015232563018798828,
"load scripts/external_code.py": 0.0010516643524169922,
"load scripts/global_state.py": 0.0,
"load scripts/hook.py": 0.0010027885437011719,
"load scripts/infotext.py": 0.0,
"load scripts/logging.py": 0.0010135173797607422,
"load scripts/lvminthin.py": 0.0,
"load scripts/movie2movie.py": 0.0,
"load scripts/supported_preprocessor.py": 0.001506805419921875,
"load scripts/utils.py": 0.0011930465698242188,
"load scripts/xyz_grid_support.py": 0.0,
"load scripts/tagger.py": 0.14598941802978516,
"load scripts/comments.py": 0.044586181640625,
"load scripts/refiner.py": 0.0010988712310791016,
"load scripts/sampler.py": 0.0009937286376953125,
"load scripts/seed.py": 0.0015211105346679688,
"load scripts": 3.618171453475952,
"load upscalers": 0.004336118698120117,
"refresh VAE": 0.0010046958923339844,
"refresh textual inversion templates": 0.0010097026824951172,
"scripts list_optimizers": 0.0010306835174560547,
"scripts list_unets": 0.0,
"reload hypernetworks": 0.0009660720825195312,
"initialize extra networks": 0.0998542308807373,
"scripts before_ui_callback": 0.01022028923034668,
"create ui": 40.41819214820862,
"gradio launch": 0.772036075592041,
"add APIs": 0.019764184951782227,
"app_started_callback/lora_script.py": 0.0,
"app_started_callback/api.py": 0.003812551498413086,
"app_started_callback/tagger.py": 0.003056764602661133,
"app_started_callback": 0.006869316101074219
}
},
"Packages": [
"absl-py==2.3.1",
"accelerate==0.21.0",
"addict==2.4.0",
"aenum==3.1.16",
"aiofiles==23.2.1",
"aiohappyeyeballs==2.6.1",
"aiohttp==3.12.14",
"aiosignal==1.4.0",
"albumentations==1.4.3",
"alembic==1.16.4",
"altair==5.5.0",
"antlr4-python3-runtime==4.9.3",
"anyio==3.7.1",
"astunparse==1.6.3",
"async-timeout==5.0.1",
"attrs==25.3.0",
"basicsr==1.4.2",
"beautifulsoup4==4.13.4",
"blendmodes==2022",
"certifi==2025.7.9",
"cffi==1.17.1",
"charset-normalizer==3.4.2",
"clean-fid==0.1.35",
"click==8.2.1",
"clip @ git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1",
"colorama==0.4.6",
"coloredlogs==15.0.1",
"colorlog==6.9.0",
"contourpy==1.3.2",
"controlnet_aux==0.0.10",
"cssselect2==0.8.0",
"cycler==0.12.1",
"Cython==3.1.2",
"deepdanbooru==1.0.4",
"deprecation==2.1.0",
"depth_anything @ https://github.com/huchenlei/Depth-Anything/releases/download/v1.0.0/depth_anything-2024.1.22.0-py2.py3-none-any.whl#sha256=26c1d38b8c3c306b4a2197d725a4b989ff65f7ebcf4fb5a96a1b6db7fbd56780",
"depth_anything_v2 @ https://github.com/MackinationsAi/UDAV2-ControlNet/releases/download/v1.0.0/depth_anything_v2-2024.7.1.0-py2.py3-none-any.whl#sha256=6848128867d1f7c7519d88df0f88bfab89100dc5225259c4d7cb90325c308c9f",
"diffusers==0.30.2",
"diskcache==5.6.3",
"dsine @ https://github.com/sdbds/DSINE/releases/download/1.0.2/dsine-2024.3.23-py3-none-any.whl#sha256=b9ea3bacce09f9b3f7fb4fa12471da7e465b2f9a60412711105a9238db280442",
"easydict==1.13",
"einops==0.4.1",
"exceptiongroup==1.3.0",
"facexlib==0.3.0",
"fastapi==0.94.0",
"ffmpy==0.6.0",
"filelock==3.18.0",
"filterpy==1.4.5",
"flatbuffers==25.2.10",
"fonttools==4.58.5",
"frozenlist==1.7.0",
"fsspec==2025.5.1",
"ftfy==6.3.1",
"future==1.0.0",
"fvcore==0.1.5.post20221221",
"gast==0.6.0",
"gdown==5.2.0",
"geffnet==1.0.2",
"gfpgan @ git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379",
"gitdb==4.0.12",
"GitPython==3.1.32",
"glob2==0.5",
"google-pasta==0.2.0",
"gradio==3.41.2",
"gradio_client==0.5.0",
"greenlet==3.2.3",
"grpcio==1.73.1",
"h11==0.12.0",
"h5py==3.14.0",
"handrefinerportable @ https://github.com/huchenlei/HandRefinerPortable/releases/download/v1.0.1/handrefinerportable-2024.2.12.0-py2.py3-none-any.whl#sha256=1e6c702905919f4c49bcb2db7b20d334e8458a7555cd57630600584ec38ca6a9",
"httpcore==0.15.0",
"httpx==0.24.1",
"huggingface-hub==0.33.4",
"humanfriendly==10.0",
"idna==3.10",
"imageio==2.37.0",
"importlib_metadata==8.7.0",
"importlib_resources==6.5.2",
"inflection==0.5.1",
"insightface @ https://github.com/Gourieff/Assets/raw/main/Insightface/insightface-0.7.3-cp310-cp310-win_amd64.whl#sha256=47aa0571b2aadd8545d4bc7615dfbc374c10180c283b7ac65058fcb41ed4df86",
"iopath==0.1.9",
"jax==0.6.2",
"jaxlib==0.6.2",
"Jinja2==3.1.6",
"joblib==1.5.1",
"jsonmerge==1.8.0",
"jsonschema==4.24.0",
"jsonschema-specifications==2025.4.1",
"keras==3.10.0",
"kiwisolver==1.4.8",
"kornia==0.6.7",
"lark==1.1.2",
"lazy_loader==0.4",
"libclang==18.1.1",
"lightning-utilities==0.14.3",
"llvmlite==0.44.0",
"lmdb==1.7.2",
"lpips==0.1.4",
"lxml==6.0.0",
"Mako==1.3.10",
"manifold3d==3.1.1",
"mapbox_earcut==1.0.3",
"Markdown==3.8.2",
"markdown-it-py==3.0.0",
"MarkupSafe==2.1.5",
"matplotlib==3.10.3",
"mdurl==0.1.2",
"mediapipe==0.10.21",
"ml_dtypes==0.5.1",
"mpmath==1.3.0",
"multidict==6.6.3",
"namex==0.1.0",
"narwhals==1.46.0",
"networkx==3.4.2",
"numba==0.61.2",
"numpy==1.26.4",
"olive-ai==0.9.1",
"omegaconf==2.2.3",
"onnx==1.16.2",
"onnx-ir==0.1.4",
"onnxruntime==1.22.1",
"onnxscript==0.3.2",
"open-clip-torch==2.20.0",
"opencv-contrib-python==4.11.0.86",
"opencv-python==4.11.0.86",
"opencv-python-headless==4.11.0.86",
"opt_einsum==3.4.0",
"optimum==1.26.1",
"optree==0.16.0",
"optuna==4.4.0",
"orjson==3.10.18",
"packaging==25.0",
"pandas==2.3.1",
"piexif==1.1.3",
"pillow==10.4.0",
"pillow-avif-plugin==1.4.3",
"pip==25.1.1",
"platformdirs==4.3.8",
"portalocker==3.2.0",
"prettytable==3.16.0",
"propcache==0.3.2",
"protobuf==5.29.5",
"psutil==5.9.5",
"pycollada==0.9.2",
"pycparser==2.22",
"pydantic==1.10.17",
"pydub==0.25.1",
"Pygments==2.19.2",
"pyparsing==3.2.3",
"pyreadline3==3.5.4",
"PySocks==1.7.1",
"python-dateutil==2.9.0.post0",
"python-multipart==0.0.20",
"pytorch-lightning==1.9.4",
"pytz==2025.2",
"PyWavelets==1.8.0",
"pywin32==310",
"PyYAML==6.0.2",
"referencing==0.36.2",
"regex==2024.11.6",
"reportlab==4.4.2",
"requests==2.32.4",
"resize-right==0.0.2",
"rich==14.0.0",
"rpds-py==0.26.0",
"rtree==1.4.0",
"safetensors==0.4.2",
"scikit-image==0.25.2",
"scikit-learn==1.7.0",
"scipy==1.15.3",
"semantic-version==2.10.0",
"sentencepiece==0.2.0",
"setuptools==69.5.1",
"shapely==2.1.1",
"six==1.17.0",
"smmap==5.0.2",
"sniffio==1.3.1",
"sounddevice==0.5.2",
"soupsieve==2.7",
"spandrel==0.3.4",
"spandrel_extra_arches==0.1.1",
"SQLAlchemy==2.0.41",
"starlette==0.26.1",
"svg.path==7.0",
"svglib==1.5.1",
"sympy==1.14.0",
"tabulate==0.9.0",
"tb-nightly==2.20.0a20250711",
"tensorboard==2.19.0",
"tensorboard-data-server==0.7.2",
"tensorflow==2.19.0",
"tensorflow-io-gcs-filesystem==0.31.0",
"termcolor==3.1.0",
"threadpoolctl==3.6.0",
"tifffile==2025.5.10",
"timm==0.9.5",
"tinycss2==1.4.0",
"tokenizers==0.21.2",
"tomesd==0.1.3",
"tomli==2.2.1",
"torch==2.0.0",
"torch-directml==0.2.0.dev230426",
"torchdiffeq==0.2.3",
"torchmetrics==1.7.4",
"torchsde==0.2.6",
"torchvision==0.15.1",
"tqdm==4.67.1",
"trampoline==0.1.2",
"transformers==4.49.0",
"trimesh==4.7.0",
"typing_extensions==4.14.1",
"tzdata==2025.2",
"urllib3==2.5.0",
"uvicorn==0.35.0",
"vhacdx==0.0.8.post2",
"wcwidth==0.2.13",
"webencodings==0.5.1",
"websockets==11.0.3",
"Werkzeug==3.1.3",
"wheel==0.45.1",
"wrapt==1.17.2",
"xxhash==3.5.0",
"yacs==0.1.8",
"yapf==0.43.0",
"yarl==1.20.1",
"zipp==3.23.0"
]
}
Console logs
venv "D:\sd_directml\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Commit hash: 6d85a7dfa4977ae4eece9cbbab4725123833be14
Installing requirements
loading WD14-tagger reqs from D:\sd_directml\extensions\stable-diffusion-webui-wd14-tagger\requirements.txt
Checking WD14-tagger requirements.
Launching Web UI with arguments: --autolaunch --precision full --skip-torch-cuda-test --opt-sdp-attention --use-directml --lowvram --no-half-vae --autolaunch --precision full --skip-torch-cuda-test --opt-sdp-attention --use-directml --lowvram --no-half-vae
2025-07-13 11:08:42.939440: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-07-13 11:08:45.640065: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
ONNX failed to initialize: Failed to import optimum.onnxruntime.modeling_diffusion because of the following error (look up to see its traceback):
Failed to import transformers.modeling_tf_utils because of the following error (look up to see its traceback):
Your currently installed version of Keras is Keras 3, but this is not yet supported in Transformers. Please install the backwards-compatible tf-keras package with `pip install tf-keras`.
==============================================================================
You are running torch 2.0.0+cpu.
The program is tested to work with torch 2.1.2.
To reinstall the desired version, run with commandline flag --reinstall-torch.
Beware that this will cause a lot of large files to be downloaded, as well as
there are reports of issues with training tab on the latest version.
Use --skip-version-check commandline argument to disable this check.
==============================================================================
ControlNet preprocessor location: D:\sd_directml\extensions\sd-webui-controlnet\annotator\downloads
2025-07-13 11:08:56,379 - ControlNet - INFO - ControlNet v1.1.455
== WD14 tagger /gpu:0, uname_result(system='Windows', node='DESKTOP-GBPLTQV', release='10', version='10.0.26100', machine='AMD64') ==
Loading weights [2e13269995] from D:\sd_directml\models\Stable-diffusion\novaOrangeXL_reV10.safetensors
Creating model from config: D:\sd_directml\repositories\generative-models\configs\inference\sd_xl_base.yaml
Loading VAE weights specified in settings: D:\sd_directml\models\VAE\sdxlVAE_sdxlVAE.safetensors
Applying attention optimization: sdp... done.
Model loaded in 36.5s (load weights from disk: 0.6s, create model: 0.9s, apply weights to model: 25.6s, apply half(): 0.3s, apply dtype to VAE: 0.1s, load VAE: 3.2s, load weights from state dict: 0.2s, move model to device: 0.3s, hijack: 1.0s, load textual inversion embeddings: 1.9s, calculate empty prompt: 2.3s).
2025-07-13 11:09:36,520 - ControlNet - INFO - ControlNet UI callback registered.
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Startup time: 117.8s (launcher: 35.0s, import torch: 21.2s, import gradio: 1.7s, setup paths: 12.2s, initialize shared: 2.6s, load scripts: 3.6s, create ui: 40.4s, gradio launch: 0.8s).
Couldn't find VAE named sdxl_vae.safetensors; using None instead
Restoring base VAE
Applying attention optimization: sdp... done.
VAE weights loaded.
100%|██████████████████████████████████████████████████████████████████████████████████| 27/27 [07:00<00:00, 15.56s/it]
0%| | 0/27 [00:00<?, ?it/s]
Loading VAE weights specified in settings: D:\sd_directml\models\VAE\sdxlVAE_sdxlVAE.safetensors
Applying attention optimization: sdp... done.
VAE weights loaded.
*** Error completing request
*** Arguments: ('task(tblrxw7xt728m2a)', <gradio.routes.Request object at 0x00000142C4CDE1D0>, 'beautiful girl, masterpiece, best quality, ultra-detailed face,beautiful eyes,Well-arranged eyes,\nshort layered bob haircut,purple eyes, slightly upturned nose,(smile:0.5),small nose,\ndeep violet hair with mint green gradient tips, smooth shiny hair, slightly tousled, detailed hair strands, natural skin texture,\nslim yet curvy body, slender waist, wide hips, hourglass figure, youthful proportions,\nnatural-looking large breasts, C-cup, smooth cleavage,\nlong legs, plump thighs, soft skin, firm hips, well-defined back curve, shapely arms, elegant neck,\nrealistic yet anime-inspired body proportions,height around 165cm,\nwhite dress shirt, glossy slightly,sleeves casually rolled up to elbows,\ntop buttons undone, teal necktie, loosely tied, natural drape,\nshort pleated skirt, (beige and brown plaid pattern), uniform style, folded waistband,\nthick fabric with sharp pleats, natural shadows, realistic light reflection,\nschool uniform inspired but casually worn,\n,on the train, train interior, front view of front seat,(looking away:1.4) ,\n(sitting:1.3),(skirt:1.3), show off panties, light blue panties,\nasakura toru, <lora:Asakura_Toru:1.2>', 'bad anatomy, poorly drawn face, asymmetrical eyes, extra hair strands, blurry face, lowres, jpeg artifacts,\nwrong hair color, wrong hairstyle, deformed, monochrome, sketch, photo\n', [], 1, 1, 5, 1056, 904, True, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', 'Use same scheduler', '', '', ['VAE: sdxl_vae.safetensors'], 0, 27, 'Euler a', 'Karras', False, '', 0.8, -1, False, -1, 0, 0, 0, <scripts.animatediff_ui.AnimateDiffProcess object at 0x00000142C4DFBC40>, ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[], batch_keyframe_idx=None), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[], batch_keyframe_idx=None), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[], batch_keyframe_idx=None), False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, False, False, False, 0, False, None, None, False, None, None, False, None, None, False, 50) {}
Traceback (most recent call last):
File "D:\sd_directml\modules\call_queue.py", line 74, in f
res = list(func(*args, **kwargs))
File "D:\sd_directml\modules\call_queue.py", line 53, in f
res = func(*args, **kwargs)
File "D:\sd_directml\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "D:\sd_directml\modules\txt2img.py", line 109, in txt2img
processed = processing.process_images(p)
File "D:\sd_directml\modules\processing.py", line 849, in process_images
res = process_images_inner(p)
File "D:\sd_directml\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 59, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
File "D:\sd_directml\modules\processing.py", line 1083, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
File "D:\sd_directml\modules\processing.py", line 1457, in sample
return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
File "D:\sd_directml\modules\processing.py", line 1549, in sample_hr_pass
samples = self.sampler.sample_img2img(self, samples, noise, self.hr_c, self.hr_uc, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
File "D:\sd_directml\modules\sd_samplers_kdiffusion.py", line 187, in sample_img2img
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "D:\sd_directml\modules\sd_samplers_common.py", line 272, in launch_sampling
return func()
File "D:\sd_directml\modules\sd_samplers_kdiffusion.py", line 187, in <lambda>
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "D:\sd_directml\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\sd_directml\repositories\k-diffusion\k_diffusion\sampling.py", line 145, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd_directml\modules\sd_samplers_cfg_denoiser.py", line 268, in forward
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(c_crossattn, image_cond_in[a:b]))
File "D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd_directml\repositories\k-diffusion\k_diffusion\external.py", line 112, in forward
eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
File "D:\sd_directml\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
File "D:\sd_directml\modules\sd_models_xl.py", line 43, in apply_model
return self.model(x, t, cond)
File "D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd_directml\modules\sd_hijack_utils.py", line 22, in <lambda>
setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
File "D:\sd_directml\modules\sd_hijack_utils.py", line 34, in __call__
return self.__sub_func(self.__orig_func, *args, **kwargs)
File "D:\sd_directml\modules\sd_hijack_unet.py", line 50, in apply_model
result = orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs)
File "D:\sd_directml\repositories\generative-models\sgm\modules\diffusionmodules\wrappers.py", line 28, in forward
return self.diffusion_model(
File "D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd_directml\modules\sd_unet.py", line 91, in UNetModel_forward
return original_forward(self, x, timesteps, context, *args, **kwargs)
File "D:\sd_directml\repositories\generative-models\sgm\modules\diffusionmodules\openaimodel.py", line 993, in forward
h = module(h, emb, context)
File "D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1538, in _call_impl
result = forward_call(*args, **kwargs)
File "D:\sd_directml\repositories\generative-models\sgm\modules\diffusionmodules\openaimodel.py", line 100, in forward
x = layer(x, context)
File "D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd_directml\repositories\generative-models\sgm\modules\attention.py", line 627, in forward
x = block(x, context=context[i])
File "D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd_directml\repositories\generative-models\sgm\modules\attention.py", line 459, in forward
return checkpoint(
File "D:\sd_directml\repositories\generative-models\sgm\modules\diffusionmodules\util.py", line 167, in checkpoint
return func(*inputs)
File "D:\sd_directml\repositories\generative-models\sgm\modules\attention.py", line 467, in _forward
self.attn1(
File "D:\sd_directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd_directml\modules\sd_hijack_optimizations.py", line 547, in scaled_dot_product_attention_forward
hidden_states = torch.nn.functional.scaled_dot_product_attention(
RuntimeError
---
Additional information
Operating System: Windows 11 Insider Preview (Build 26100). I am aware this is a pre-release build and might be a contributing factor to the instability.
GPU Driver: Intel Graphics Driver version 32.0.101.6913. I regularly update my drivers to the latest available.
Problem Summary: The issue consistently occurs during the Highres. fix step of image generation (specifically with SDXL models), leading to a RuntimeError. This happens when upscaling with a Denoising strength of 0.7 or higher, even at relatively low base resolutions
VRAM Management: I have confirmed that the "VRAM usage polls per second" setting was at 8 and will change it to 0 as suggested.
Commandline Args: I've identified that my webui-user.bat file contains duplicate COMMANDLINE_ARGS entries and will correct this.
PyTorch-DirectML Version: My torch-directml version is 0.2.0.dev230426, which seems to be an older development version. I plan to attempt to update it.
Extensions: While the provided log was generated with extensions active, the issue has also persisted when --disable-all-extensions was enabled (I will re-test if needed).
System RAM: My system has 16GB of RAM, with approximately 12GB typically in use before starting the WebUI. I make an effort to close other applications to free up RAM during image generation.
stable-diffusion-webui copied to clipboard
AUTOMATIC1111
