Describe the bug
I found the most peculiar bug. I have RegPro working as intended in 'Active' mode. Multiple Loras, Open Pose enable, x/y/z Prompter enabled with different Denoising settings.
Now I switch to 'Latent' mode and I get an 'Latent mode not implemented' in latent.py.
I switch back to Active mode and I still get the latent not implemented error.
I disable everything. No Loras, no Controlnet, no Script. Latent works.
I add loras back, latent works, I add scripts back, latent works. I add Open Pose back, latent works.
WTF
Error Stack:
2024-02-25 15:42:28,026 - ControlNet - INFO - unit_separate = False, style_align = False
2024-02-25 15:42:28,026 - ControlNet - INFO - Loading model from cache: control_v11p_sd15_openpose [cab727d4]
2024-02-25 15:42:28,080 - ControlNet - INFO - Using preprocessor: dw_openpose_full
2024-02-25 15:42:28,080 - ControlNet - INFO - preprocessor resolution = 453
2024-02-25 15:42:28,269 - ControlNet - INFO - ControlNet Hooked - Time = 0.24901032447814941
Warning: Nonstandard height / width for ulscaled size
1,1,1,1,1;3,1,1,1,1,1,1,1 0.2 Horizontal
Regional Prompter Active, Pos tokens : [17, 0, 27, 31, 0, 0, 0, 2, 45, 0, 7, 0, 1], Neg tokens : [295]
generating image for xyz plot: NotImplementedError
Traceback (most recent call last):
File "C:\Users\NAME\stable-diffusion-webui\scripts\xyz_grid.py", line 701, in cell
res = process_images(pc)
File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 734, in process_images
res = process_images_inner(p)
File "C:\Users\NAME\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 41, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, kwargs)
File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 857, in process_images_inner
p.setup_conds()
File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 1308, in setup_conds
super().setup_conds()
File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 469, in setup_conds
self.uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, total_steps, [self.cached_uc], self.extra_network_data)
File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 455, in get_conds_with_caching
cache[1] = function(shared.sd_model, required_prompts, steps, hires_steps, shared.opts.use_old_scheduling)
File "C:\Users\NAME\stable-diffusion-webui\modules\prompt_parser.py", line 188, in get_learned_conditioning
conds = model.get_learned_conditioning(texts)
File "C:\Users\NAME\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 669, in get_learned_conditioning
c = self.cond_stage_model(c)
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, *kwargs)
File "C:\Users\NAME\stable-diffusion-webui\modules\sd_hijack_clip.py", line 234, in forward
z = self.process_tokens(tokens, multipliers)
File "C:\Users\NAME\stable-diffusion-webui\modules\sd_hijack_clip.py", line 273, in process_tokens
z = self.encode_with_transformers(tokens)
File "C:\Users\NAME\stable-diffusion-webui\modules\sd_hijack_clip.py", line 326, in encode_with_transformers
outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers)
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(args, kwargs)
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 822, in forward
return self.text_model(
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, kwargs)
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 740, in forward
encoder_outputs = self.encoder(
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, *kwargs)
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 654, in forward
layer_outputs = encoder_layer(
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(args, kwargs)
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 383, in forward
hidden_states, attn_weights = self.self_attn(
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, kwargs)
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 272, in forward
query_states = self.q_proj(hidden_states) self.scale
File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(args, kwargs)
File "C:\Users\NAME\stable-diffusion-webui\extensions\sd-webui-regional-prompter\scripts\latent.py", line 498, in h_Linear_forward
return networks.network_forward(self, input, networks.originals.Linear_forward)
File "C:\Users\NAME\stable-diffusion-webui\extensions-builtin\Lora\networks.py", line 469, in network_forward
y = module.forward(input, y)
File "C:\Users\NAME\stable-diffusion-webui\extensions-builtin\Lora\network.py", line 158, in forward
raise NotImplementedError()
NotImplementedError
Environment
Web-UI version:
version: v1.7.0 • python: 3.10.11 • torch: 2.0.1+cu118 • xformers: 0.0.20 • gradio: 3.41.2
SD Version: 1.7 I guess
LoRA several Lora, but they don't seem to be issue
Other Enabled Extensions
--
DWPose https://github.com/IDEA-Research/DWPose onnx [3dca5db7](https://github.com/IDEA-Research/DWPose/commit/3dca5db79d9f9ffdd378753ddf6ec66535aace88) 2023-12-12 03:54:23 unknown
TemporalKit https://github.com/CiaraStrawberry/TemporalKit main [f46d255c](https://github.com/CiaraStrawberry/TemporalKit/commit/f46d255cfeb9c4b0c682bae5660a04ac7b7cd8dc) 2023-10-04 00:10:32 unknown
sd-webui-controlnet https://github.com/Mikubill/sd-webui-controlnet.git main [679b6279](https://github.com/Mikubill/sd-webui-controlnet/commit/679b62790b22319a6833130c23986fb4fa47337b) 2024-02-19 03:52:46 unknown
sd-webui-extended-style-saver https://github.com/harukei-tech/sd-webui-extended-style-saver.git master [7750cc6b](https://github.com/harukei-tech/sd-webui-extended-style-saver/commit/7750cc6b2dcba91951402a682819bcb4fcc43bea) 2024-01-07 06:45:31 unknown
sd-webui-openpose-editor https://github.com/huchenlei/sd-webui-openpose-editor.git main [cebe13e0](https://github.com/huchenlei/sd-webui-openpose-editor/commit/cebe13e092fa3c5d810f4afbd7a45987ba8275d0) 2023-12-19 04:58:26 unknown
sd-webui-reactor https://github.com/Gourieff/sd-webui-reactor.git main [778ddec9](https://github.com/Gourieff/sd-webui-reactor/commit/778ddec96d92c46e2d9cd6a8721930edd13fc894) 2024-02-24 13:57:46 unknown
sd-webui-regional-prompter https://github.com/hako-mikan/sd-webui-regional-prompter.git main [59d68e6e](https://github.com/hako-mikan/sd-webui-regional-prompter/commit/59d68e6e1c49fe2df1e1b483dc0fe6621467435a) 2024-02-07 17:24:12 unknown
sd_save_intermediate_images https://github.com/AlUlkesh/sd_save_intermediate_images.git main [24c3ce20](https://github.com/AlUlkesh/sd_save_intermediate_images/commit/24c3ce206a6493c3180fb71a970d5f122cc52fba) 2023-10-10 15:24:31 unknown
stable-diffusion-webui-images-browser https://github.com/AlUlkesh/stable-diffusion-webui-images-browser.git main [3d2d0f4c](https://github.com/AlUlkesh/stable-diffusion-webui-images-browser/commit/3d2d0f4c7b0599f88df99a9ea66c21bcbec49bda) 2024-02-02 15:40:47 unknown
Describe the bug I found the most peculiar bug. I have RegPro working as intended in 'Active' mode. Multiple Loras, Open Pose enable, x/y/z Prompter enabled with different Denoising settings. Now I switch to 'Latent' mode and I get an 'Latent mode not implemented' in latent.py. I switch back to Active mode and I still get the latent not implemented error. I disable everything. No Loras, no Controlnet, no Script. Latent works. I add loras back, latent works, I add scripts back, latent works. I add Open Pose back, latent works.
WTF
Error Stack: 2024-02-25 15:42:28,026 - ControlNet - INFO - unit_separate = False, style_align = False 2024-02-25 15:42:28,026 - ControlNet - INFO - Loading model from cache: control_v11p_sd15_openpose [cab727d4] 2024-02-25 15:42:28,080 - ControlNet - INFO - Using preprocessor: dw_openpose_full 2024-02-25 15:42:28,080 - ControlNet - INFO - preprocessor resolution = 453 2024-02-25 15:42:28,269 - ControlNet - INFO - ControlNet Hooked - Time = 0.24901032447814941 Warning: Nonstandard height / width for ulscaled size 1,1,1,1,1;3,1,1,1,1,1,1,1 0.2 Horizontal Regional Prompter Active, Pos tokens : [17, 0, 27, 31, 0, 0, 0, 2, 45, 0, 7, 0, 1], Neg tokens : [295] generating image for xyz plot: NotImplementedError Traceback (most recent call last): File "C:\Users\NAME\stable-diffusion-webui\scripts\xyz_grid.py", line 701, in cell res = process_images(pc) File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 734, in process_images res = process_images_inner(p) File "C:\Users\NAME\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 41, in processing_process_images_hijack return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, kwargs) File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 857, in process_images_inner p.setup_conds() File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 1308, in setup_conds super().setup_conds() File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 469, in setup_conds self.uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, total_steps, [self.cached_uc], self.extra_network_data) File "C:\Users\NAME\stable-diffusion-webui\modules\processing.py", line 455, in get_conds_with_caching cache[1] = function(shared.sd_model, required_prompts, steps, hires_steps, shared.opts.use_old_scheduling) File "C:\Users\NAME\stable-diffusion-webui\modules\prompt_parser.py", line 188, in get_learned_conditioning conds = model.get_learned_conditioning(texts) File "C:\Users\NAME\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 669, in get_learned_conditioning c = self.cond_stage_model(c) File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "C:\Users\NAME\stable-diffusion-webui\modules\sd_hijack_clip.py", line 234, in forward z = self.process_tokens(tokens, multipliers) File "C:\Users\NAME\stable-diffusion-webui\modules\sd_hijack_clip.py", line 273, in process_tokens z = self.encode_with_transformers(tokens) File "C:\Users\NAME\stable-diffusion-webui\modules\sd_hijack_clip.py", line 326, in encode_with_transformers outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers) File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 822, in forward return self.text_model( File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 740, in forward encoder_outputs = self.encoder( File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 654, in forward layer_outputs = encoder_layer( File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 383, in forward hidden_states, attn_weights = self.self_attn( File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 272, in forward query_states = self.q_proj(hidden_states) self.scale File "C:\Users\NAME\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "C:\Users\NAME\stable-diffusion-webui\extensions\sd-webui-regional-prompter\scripts\latent.py", line 498, in h_Linear_forward return networks.network_forward(self, input, networks.originals.Linear_forward) File "C:\Users\NAME\stable-diffusion-webui\extensions-builtin\Lora\networks.py", line 469, in network_forward y = module.forward(input, y) File "C:\Users\NAME\stable-diffusion-webui\extensions-builtin\Lora\network.py", line 158, in forward raise NotImplementedError() NotImplementedError
Environment Web-UI version: version: v1.7.0 • python: 3.10.11 • torch: 2.0.1+cu118 • xformers: 0.0.20 • gradio: 3.41.2 SD Version: 1.7 I guess LoRA several Lora, but they don't seem to be issue
Other Enabled Extensions
-- DWPose https://github.com/IDEA-Research/DWPose onnx [3dca5db7](https://github.com/IDEA-Research/DWPose/commit/3dca5db79d9f9ffdd378753ddf6ec66535aace88) 2023-12-12 03:54:23 unknown TemporalKit https://github.com/CiaraStrawberry/TemporalKit main [f46d255c](https://github.com/CiaraStrawberry/TemporalKit/commit/f46d255cfeb9c4b0c682bae5660a04ac7b7cd8dc) 2023-10-04 00:10:32 unknown sd-webui-controlnet https://github.com/Mikubill/sd-webui-controlnet.git main [679b6279](https://github.com/Mikubill/sd-webui-controlnet/commit/679b62790b22319a6833130c23986fb4fa47337b) 2024-02-19 03:52:46 unknown sd-webui-extended-style-saver https://github.com/harukei-tech/sd-webui-extended-style-saver.git master [7750cc6b](https://github.com/harukei-tech/sd-webui-extended-style-saver/commit/7750cc6b2dcba91951402a682819bcb4fcc43bea) 2024-01-07 06:45:31 unknown sd-webui-openpose-editor https://github.com/huchenlei/sd-webui-openpose-editor.git main [cebe13e0](https://github.com/huchenlei/sd-webui-openpose-editor/commit/cebe13e092fa3c5d810f4afbd7a45987ba8275d0) 2023-12-19 04:58:26 unknown sd-webui-reactor https://github.com/Gourieff/sd-webui-reactor.git main [778ddec9](https://github.com/Gourieff/sd-webui-reactor/commit/778ddec96d92c46e2d9cd6a8721930edd13fc894) 2024-02-24 13:57:46 unknown sd-webui-regional-prompter https://github.com/hako-mikan/sd-webui-regional-prompter.git main [59d68e6e](https://github.com/hako-mikan/sd-webui-regional-prompter/commit/59d68e6e1c49fe2df1e1b483dc0fe6621467435a) 2024-02-07 17:24:12 unknown sd_save_intermediate_images https://github.com/AlUlkesh/sd_save_intermediate_images.git main [24c3ce20](https://github.com/AlUlkesh/sd_save_intermediate_images/commit/24c3ce206a6493c3180fb71a970d5f122cc52fba) 2023-10-10 15:24:31 unknown stable-diffusion-webui-images-browser https://github.com/AlUlkesh/stable-diffusion-webui-images-browser.git main [3d2d0f4c](https://github.com/AlUlkesh/stable-diffusion-webui-images-browser/commit/3d2d0f4c7b0599f88df99a9ea66c21bcbec49bda) 2024-02-02 15:40:47 unknown