search

lllyasviel / sd-forge-layerdiffuse

[WIP] Layer Diffusion for WebUI (via Forge)
Apache License 2.0
3.86k stars 331 forks source link

for sd 1.5 ,RuntimeError: CUDA error: invalid configuration argument #74

Open sdcarterchen opened 7 months ago

sdcarterchen commented 7 months ago

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: f0.0.17v1.8.0rc-latest-276-g29be1da7 Commit hash: 29be1da7cf2b5dccfc70fbdd33eb35c56a31ffb7 CUDA 12.1 Launching Web UI with arguments: --xformers --ckpt-dir J:\AI\condaEnv\stable-diffusion-webui/models/Stable-diffusion --hypernetwork-dir J:\AI\condaEnv\stable-diffusion-webui/models/hypernetworks --embeddings-dir J:\AI\condaEnv\stable-diffusion-webui/embeddings --lora-dir J:\AI\condaEnv\stable-diffusion-webui/models/Lora --vae-dir J:\AI\condaEnv\stable-diffusion-webui/models/VAE Total VRAM 8192 MB, total RAM 32646 MB xformers version: 0.0.24 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3070 Ti : native Hint: your device supports --pin-shared-memory for potential speed improvements. Hint: your device supports --cuda-malloc for potential speed improvements. Hint: your device supports --cuda-stream for potential speed improvements. VAE dtype: torch.bfloat16 CUDA Stream Activated: False Using xformers cross attention ControlNet preprocessor location: J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\models\ControlNetPreprocessor [-] ADetailer initialized. version: 24.1.2, num models: 16 sd-webui-prompt-all-in-one background API service started successfully. 01:37:21 - ReActor - STATUS - Running v0.7.0-a2 on Device: CUDA Loading weights [15012c538f] from J:\AI\condaEnv\stable-diffusion-webui\models\Stable-diffusion\realisticVisionV51_v51VAE.safetensors 2024-03-13 01:37:22,668 - ControlNet - INFO - ControlNet UI callback registered. model_type EPS UNet ADM Dimension 0 Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Using xformers attention in VAE Working with z of shape (1, 4, 32, 32) = 4096 dimensions. Using xformers attention in VAE Startup time: 119.9s (prepare environment: 5.9s, import torch: 5.1s, import gradio: 1.1s, setup paths: 0.6s, initialize shared: 0.3s, other imports: 0.6s, load scripts: 103.3s, create ui: 0.9s, gradio launch: 1.0s, app_started_callback: 0.8s). extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'} To load target model SD1ClipModel Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 7091.9296875 [Memory Management] Model Memory (MB) = 454.2076225280762 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 5613.722064971924 Moving model(s) has taken 0.11 seconds Model loaded in 4.2s (load weights from disk: 0.8s, forge load real models: 2.4s, calculate empty prompt: 0.9s). To load target model BaseModel Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 6730.8017578125 [Memory Management] Model Memory (MB) = 1639.4137649536133 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 4067.3879928588867 Moving model(s) has taken 0.41 seconds 100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.73it/s] To load target model AutoencoderKL█████████████████████████████████████████████████████| 20/20 [00:01<00:00, 13.58it/s] Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 5061.75244140625 [Memory Management] Model Memory (MB) = 159.55708122253418 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 3878.195360183716 Moving model(s) has taken 0.13 seconds Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.53it/s] 100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 5.04it/s] Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00, 4.43it/s] [Layer Diffusion] LayerMethod.JOINT_SD15███████████████████████████████████████████████| 20/20 [00:04<00:00, 5.37it/s] Reuse 1 loaded models To load target model BaseModel Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 4879.0224609375 [Memory Management] Model Memory (MB) = 0.0 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 3855.0224609375 Moving model(s) has taken 0.55 seconds 0%| | 0/20 [00:00<?, ?it/s] Traceback (most recent call last): File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules_forge\main_thread.py", line 37, in loop task.work() File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules_forge\main_thread.py", line 26, in work self.result = self.func(*self.args, self.kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\txt2img.py", line 111, in txt2img_function processed = processing.process_images(p) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\processing.py", line 752, in process_images res = process_images_inner(p) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\processing.py", line 922, 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 "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\processing.py", line 1275, in sample samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\sd_samplers_kdiffusion.py", line 251, in sample samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, extra_params_kwargs)) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\sd_samplers_common.py", line 263, in launch_sampling return func() File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\sd_samplers_kdiffusion.py", line 251, in samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, extra_params_kwargs)) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\repositories\k-diffusion\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m denoised = model(x, sigmas[i] s_in, extra_args) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\sd_samplers_cfg_denoiser.py", line 182, in forward denoised = forge_sampler.forge_sample(self, denoiser_params=denoiser_params, File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules_forge\forge_sampler.py", line 88, in forge_sample denoised = sampling_function(model, x, timestep, uncond, cond, cond_scale, model_options, seed) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\modules\samplers.py", line 289, in sampling_function cond_pred, uncond_pred = calc_cond_uncondbatch(model, cond, uncond, x, timestep, model_options) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\modules\samplers.py", line 258, in calc_cond_uncond_batch output = model.apply_model(inputx, timestep, c).chunk(batch_chunks) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\modules\model_base.py", line 90, in apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, *extra_conds).float() File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\diffusionmodules\openaimodel.py", line 867, in forward h = forward_timestep_embed(module, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\diffusionmodules\openaimodel.py", line 55, in forward_timestep_embed x = layer(x, context, transformer_options) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\attention.py", line 620, in forward x = block(x, context=context[i], transformer_options=transformer_options) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\attention.py", line 447, in forward return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\diffusionmodules\util.py", line 194, in checkpoint return func(inputs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\attention.py", line 507, in _forward n = self.attn1(n, context=context_attn1, value=value_attn1, transformer_options=extra_options) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\extensions\sd-forge-layerdiffuse\lib_layerdiffusion\attention_sharing.py", line 131, in forward x = optimized_attention(q, k, v, self.heads) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\attention.py", line 314, in attention_xformers out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=mask) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmha__init.py", line 223, in memory_efficient_attention return _memory_efficient_attention( File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmha__init.py", line 321, in _memory_efficient_attention return _memory_efficient_attention_forward( File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmha\init__.py", line 341, in _memory_efficient_attentionforward out, * = op.apply(inp, needs_gradient=False) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmha\flash.py", line 458, in apply out, softmax_lse, rng_state = cls.OPERATOR( File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch_ops.py", line 755, in call__ return self._op(*args, **(kwargs or {})) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmha\flash.py", line 106, in _flash_fwd ) = _C_flashattention.fwd( RuntimeError: CUDA error: invalid configuration argument CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

CUDA error: invalid configuration argument CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

Error completing request Arguments: ('task(tmuo2818gmet6lo)', <gradio.routes.Request object at 0x000001E094FC9510>, 'an apple on table,high quality,4k,', '(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4),(watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2),(blur, blurry, grainy),morbid,ugly,asymmetrical,mutated malformed,mutilated,poorly lit,bad shadow,draft,cropped,out of frame,cut off,censored,jpeg artifacts,out of focus,glitch,duplicate,(airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3),(3D ,3D Game, 3D Game Scene, 3D Character:1.1),(bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3),', [], 20, 'DPM++ 2M Karras', 1, 3, 6, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], 0, False, '', 0.8, 1591002429, False, -1, 0, 0, 0, False, False, {'ad_model': 'mediapipe_face_full', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, True, '(SD1.5) Generate Everything Together (need batch size 3)', 1, 1, None, None, None, 'Crop and Resize', False, '', '', '', None, False, '0', '0', 'inswapper_128.onnx', 'CodeFormer', 1, True, 'None', 1, 1, False, True, 1, 0, 0, False, 0.5, True, False, 'CUDA', False, 0, 'None', '', None, False, False, 0.5, 0, ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), False, 7, 1, 'Constant', 0, 'Constant', 0, 1, 'enable', 'MEAN', 'AD', 1, False, 1.01, 1.02, 0.99, 0.95, False, 0.5, 2, False, 256, 2, 0, False, False, 3, 2, 0, 0.35, True, 'bicubic', 'bicubic', False, 0, 'anisotropic', 0, 'reinhard', 100, 0, 'subtract', 0, 0, 'gaussian', 'add', 0, 100, 127, 0, 'hard_clamp', 5, 0, 'None', 'None', False, 'MultiDiffusion', 768, 768, 64, 4, False, False, False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, False, False, False, 0, False) {} Traceback (most recent call last): File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) TypeError: 'NoneType' object is not iterable

wly-ai-bj commented 7 months ago

same question

wly-ai-bj commented 7 months ago

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: f0.0.17v1.8.0rc-latest-276-g29be1da7 Commit hash: 29be1da7cf2b5dccfc70fbdd33eb35c56a31ffb7 CUDA 12.1 Launching Web UI with arguments: --xformers --ckpt-dir J:\AI\condaEnv\stable-diffusion-webui/models/Stable-diffusion --hypernetwork-dir J:\AI\condaEnv\stable-diffusion-webui/models/hypernetworks --embeddings-dir J:\AI\condaEnv\stable-diffusion-webui/embeddings --lora-dir J:\AI\condaEnv\stable-diffusion-webui/models/Lora --vae-dir J:\AI\condaEnv\stable-diffusion-webui/models/VAE Total VRAM 8192 MB, total RAM 32646 MB xformers version: 0.0.24 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3070 Ti : native Hint: your device supports --pin-shared-memory for potential speed improvements. Hint: your device supports --cuda-malloc for potential speed improvements. Hint: your device supports --cuda-stream for potential speed improvements. VAE dtype: torch.bfloat16 CUDA Stream Activated: False Using xformers cross attention ControlNet preprocessor location: J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\models\ControlNetPreprocessor [-] ADetailer initialized. version: 24.1.2, num models: 16 sd-webui-prompt-all-in-one background API service started successfully. 01:37:21 - ReActor - STATUS - Running v0.7.0-a2 on Device: CUDA Loading weights [15012c538f] from J:\AI\condaEnv\stable-diffusion-webui\models\Stable-diffusion\realisticVisionV51_v51VAE.safetensors 2024-03-13 01:37:22,668 - ControlNet - INFO - ControlNet UI callback registered. model_type EPS UNet ADM Dimension 0 Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Using xformers attention in VAE Working with z of shape (1, 4, 32, 32) = 4096 dimensions. Using xformers attention in VAE Startup time: 119.9s (prepare environment: 5.9s, import torch: 5.1s, import gradio: 1.1s, setup paths: 0.6s, initialize shared: 0.3s, other imports: 0.6s, load scripts: 103.3s, create ui: 0.9s, gradio launch: 1.0s, app_started_callback: 0.8s). extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'} To load target model SD1ClipModel Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 7091.9296875 [Memory Management] Model Memory (MB) = 454.2076225280762 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 5613.722064971924 Moving model(s) has taken 0.11 seconds Model loaded in 4.2s (load weights from disk: 0.8s, forge load real models: 2.4s, calculate empty prompt: 0.9s). To load target model BaseModel Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 6730.8017578125 [Memory Management] Model Memory (MB) = 1639.4137649536133 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 4067.3879928588867 Moving model(s) has taken 0.41 seconds 100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.73it/s] To load target model AutoencoderKL█████████████████████████████████████████████████████| 20/20 [00:01<00:00, 13.58it/s] Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 5061.75244140625 [Memory Management] Model Memory (MB) = 159.55708122253418 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 3878.195360183716 Moving model(s) has taken 0.13 seconds Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.53it/s] 100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 5.04it/s] Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00, 4.43it/s] [Layer Diffusion] LayerMethod.JOINT_SD15███████████████████████████████████████████████| 20/20 [00:04<00:00, 5.37it/s] Reuse 1 loaded models To load target model BaseModel Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 4879.0224609375 [Memory Management] Model Memory (MB) = 0.0 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 3855.0224609375 Moving model(s) has taken 0.55 seconds 0%| | 0/20 [00:00<?, ?it/s] Traceback (most recent call last): File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules_forge\main_thread.py", line 37, in loop task.work() File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules_forge\main_thread.py", line 26, in work self.result = self.func(*self.args, self.kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\txt2img.py", line 111, in txt2img_function processed = processing.process_images(p) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\processing.py", line 752, in process_images res = process_images_inner(p) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\processing.py", line 922, 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 "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\processing.py", line 1275, in sample samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\sd_samplers_kdiffusion.py", line 251, in sample samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, extra_params_kwargs)) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\sd_samplers_common.py", line 263, in launch_sampling return func() File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\sd_samplers_kdiffusion.py", line 251, in samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, extra_params_kwargs)) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\repositories\k-diffusion\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m denoised = model(x, sigmas[i] s_in, extra_args) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\sd_samplers_cfg_denoiser.py", line 182, in forward denoised = forge_sampler.forge_sample(self, denoiser_params=denoiser_params, File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules_forge\forge_sampler.py", line 88, in forge_sample denoised = sampling_function(model, x, timestep, uncond, cond, cond_scale, model_options, seed) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\modules\samplers.py", line 289, in sampling_function cond_pred, uncond_pred = calc_cond_uncondbatch(model, cond, uncond, x, timestep, model_options) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\modules\samplers.py", line 258, in calc_cond_uncond_batch output = model.apply_model(inputx, timestep, c).chunk(batch_chunks) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\modules\model_base.py", line 90, in apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, *extra_conds).float() File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\diffusionmodules\openaimodel.py", line 867, in forward h = forward_timestep_embed(module, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\diffusionmodules\openaimodel.py", line 55, in forward_timestep_embed x = layer(x, context, transformer_options) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\attention.py", line 620, in forward x = block(x, context=context[i], transformer_options=transformer_options) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\attention.py", line 447, in forward return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\diffusionmodules\util.py", line 194, in checkpoint return func(inputs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\attention.py", line 507, in _forward n = self.attn1(n, context=context_attn1, value=value_attn1, transformer_options=extra_options) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, kwargs) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\extensions\sd-forge-layerdiffuse\lib_layerdiffusion\attention_sharing.py", line 131, in forward x = optimized_attention(q, k, v, self.heads) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\ldm_patched\ldm\modules\attention.py", line 314, in attention_xformers out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=mask) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmhainit.py", line 223, in memory_efficient_attention return _memory_efficient_attention( File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmhainit.py", line 321, in _memory_efficient_attention return _memory_efficient_attention_forward( File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmhainit.py", line 341, in _memory_efficient_attentionforward out, * = op.apply(inp, needs_gradient=False) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmha\flash.py", line 458, in apply out, softmax_lse, rng_state = cls.OPERATOR( File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\torch_ops.py", line 755, in call return self._op(*args, **(kwargs or {})) File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\system\python\lib\site-packages\xformers\ops\fmha\flash.py", line 106, in _flash_fwd ) = _C_flashattention.fwd( RuntimeError: CUDA error: invalid configuration argument CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

CUDA error: invalid configuration argument CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

Error completing request Arguments: ('task(tmuo2818gmet6lo)', <gradio.routes.Request object at 0x000001E094FC9510>, 'an apple on table,high quality,4k,', '(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4),(watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2),(blur, blurry, grainy),morbid,ugly,asymmetrical,mutated malformed,mutilated,poorly lit,bad shadow,draft,cropped,out of frame,cut off,censored,jpeg artifacts,out of focus,glitch,duplicate,(airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3),(3D ,3D Game, 3D Game Scene, 3D Character:1.1),(bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3),', [], 20, 'DPM++ 2M Karras', 1, 3, 6, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], 0, False, '', 0.8, 1591002429, False, -1, 0, 0, 0, False, False, {'ad_model': 'mediapipe_face_full', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, True, '(SD1.5) Generate Everything Together (need batch size 3)', 1, 1, None, None, None, 'Crop and Resize', False, '', '', '', None, False, '0', '0', 'inswapper_128.onnx', 'CodeFormer', 1, True, 'None', 1, 1, False, True, 1, 0, 0, False, 0.5, True, False, 'CUDA', False, 0, 'None', '', None, False, False, 0.5, 0, ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), False, 7, 1, 'Constant', 0, 'Constant', 0, 1, 'enable', 'MEAN', 'AD', 1, False, 1.01, 1.02, 0.99, 0.95, False, 0.5, 2, False, 256, 2, 0, False, False, 3, 2, 0, 0.35, True, 'bicubic', 'bicubic', False, 0, 'anisotropic', 0, 'reinhard', 100, 0, 'subtract', 0, 0, 'gaussian', 'add', 0, 100, 127, 0, 'hard_clamp', 5, 0, 'None', 'None', False, 'MultiDiffusion', 768, 768, 64, 4, False, False, False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, False, False, False, 0, False) {} Traceback (most recent call last): File "J:\AI\condaEnv\webuiforge\webui_forge_cu121_torch21\webui\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) TypeError: 'NoneType' object is not iterable

Have you solved this problem??

lachlan-nicholson commented 7 months ago

I solved a similar error by using a different torch cuda SDP backend. Specifically the math/pytorch c++ implementation worked fine, but flash and memory-efficient attention failed.

More info here: https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html

sdcarterchen commented 7 months ago

Have you solved this problem??

I haven't solved this problem yet

wangwenqiao666 commented 7 months ago

I can use sdxl model, but using 1.5 model error like you, I use Ubuntu20.02 system, graphics card is rtx4090 ![Uploading image.png…]()

wangwenqiao666 commented 7 months ago

Error parsing "layerdiffusion_fg_additional_prompt: " Error parsing "layerdiffusion_bg_additional_prompt: " Error parsing "layerdiffusion_blend_additional_prompt: " [Layer Diffusion] LayerMethod.FG_ONLY_ATTN_SD15 To load target model BaseModel Begin to load 1 model [Memory Management] Current Free GPU Memory (MB) = 15789.16015625 [Memory Management] Model Memory (MB) = 1639.4137649536133 [Memory Management] Minimal Inference Memory (MB) = 1024.0 [Memory Management] Estimated Remaining GPU Memory (MB) = 13125.746391296387 Moving model(s) has taken 0.18 seconds

0%| | 0/20 [00:00<?, ?it/s] 0%| | 0/20 [00:00<?, ?it/s] Traceback (most recent call last): File "/data/stable-diffusion-webui-forge/modules_forge/main_thread.py", line 37, in loop task.work() File "/data/stable-diffusion-webui-forge/modules_forge/main_thread.py", line 26, in work self.result = self.func(*self.args, self.kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/modules/txt2img.py", line 111, in txt2img_function processed = processing.process_images(p) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/modules/processing.py", line 752, in process_images res = process_images_inner(p) ^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/modules/processing.py", line 922, 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 "/data/stable-diffusion-webui-forge/modules/processing.py", line 1275, in sample samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/modules/sd_samplers_kdiffusion.py", line 251, in sample samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, extra_params_kwargs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/modules/sd_samplers_common.py", line 263, in launch_sampling return func() ^^^^^^ File "/data/stable-diffusion-webui-forge/modules/sd_samplers_kdiffusion.py", line 251, in samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, extra_params_kwargs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/repositories/k-diffusion/k_diffusion/sampling.py", line 626, in sample_dpmpp_2m_sde denoised = model(x, sigmas[i] s_in, extra_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/modules/sd_samplers_cfg_denoiser.py", line 182, in forward denoised = forge_sampler.forge_sample(self, denoiser_params=denoiser_params, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/modules_forge/forge_sampler.py", line 88, in forge_sample denoised = sampling_function(model, x, timestep, uncond, cond, cond_scale, model_options, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/modules/samplers.py", line 289, in sampling_function cond_pred, uncond_pred = calc_cond_uncondbatch(model, cond, uncond, x, timestep, model_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/modules/samplers.py", line 258, in calc_cond_uncond_batch output = model.apply_model(inputx, timestep, c).chunk(batch_chunks) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/modules/model_base.py", line 90, in apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, *extra_conds).float() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/ldm/modules/diffusionmodules/openaimodel.py", line 867, in forward h = forward_timestep_embed(module, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/ldm/modules/diffusionmodules/openaimodel.py", line 55, in forward_timestep_embed x = layer(x, context, transformer_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/ldm/modules/attention.py", line 620, in forward x = block(x, context=context[i], transformer_options=transformer_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/ldm/modules/attention.py", line 447, in forward return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/ldm/modules/diffusionmodules/util.py", line 194, in checkpoint return func(inputs) ^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/ldm_patched/ldm/modules/attention.py", line 507, in _forward n = self.attn1(n, context=context_attn1, value=value_attn1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/stable-diffusion-webui-forge/extensions/sd-forge-layerdiffuse/lib_layerdiffusion/attention_sharing.py", line 92, in forward framed_cond_mark = einops.rearrange(transformer_options['cond_mark'], '(b f) -> f b', f=self.frames).to(modified_hidden_states)


KeyError: 'cond_mark'
'cond_mark'
*** Error completing request
*** Arguments: ('task(shs7sfb6ljjcptu)', <gradio.routes.Request object at 0x7fdf220578d0>, '1dog,high quality,', 'nsfw,bad,', [], 20, 'DPM++ 2M SDE Karras', 1, 1, 7, 1024, 1024, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], 0, False, '', 0.8, 3168306763, False, -1, 0, 0, 0, False, False, {'ad_model': 'mediapipe_face_full', 'ad_model_classes': '', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_model_classes': '', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, True, '(SD1.5) Only Generate Transparent Image (Attention Injection)', 1, 1, None, None, None, 'Crop and Resize', False, '', '', '', ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), False, 7, 1, 'Constant', 0, 'Constant', 0, 1, 'enable', 'MEAN', 'AD', 1, False, 1.01, 1.02, 0.99, 0.95, False, 0.5, 2, False, 256, 2, 0, False, False, 3, 2, 0, 0.35, True, 'bicubic', 'bicubic', False, 0, 'anisotropic', 0, 'reinhard', 100, 0, 'subtract', 0, 0, 'gaussian', 'add', 0, 100, 127, 0, 'hard_clamp', 5, 0, 'None', 'None', False, 'MultiDiffusion', 768, 768, 64, 4, False, False, False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, False, False, False, 0, False) {}
    Traceback (most recent call last):
      File "/data/stable-diffusion-webui-forge/modules/call_queue.py", line 57, in f
        res = list(func(*args, **kwargs))
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^
    TypeError: 'NoneType' object is not iterable

---
stormcenter commented 7 months ago

same issue, not fixed ,what for a solution

jisdf commented 6 months ago

@sdcarterchen Hello, I may have found a solution. When you need to use the sd1.5 model and need to use layerdiffuse, you need to change the cross attention to pytorch cross attention.I will have the same problem as you under the cross attention of xformers, I hope it can help you.

jisdf commented 6 months ago

@stormcenter Hello, I may have found a solution. When you need to use the sd1.5 model and need to use layerdiffuse, you need to change the cross attention to pytorch cross attention.I will have the same problem as you under the cross attention of xformers, I hope it can help you.

Muawizodux commented 3 months ago

use following flags while launching webUI --disable-xformers --opt-sdp-attention.