Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

error when loading LCM + Turbo mix LoRA #428

Open
ssube opened this issue Dec 3, 2023 · 0 comments
Open

error when loading LCM + Turbo mix LoRA #428

ssube opened this issue Dec 3, 2023 · 0 comments
Labels
model/lora scope/api status/planned issues that have been planned but not started type/bug broken features
Milestone

Comments

@ssube
Copy link
Owner

ssube commented Dec 3, 2023

[2023-12-03 22:17:23,059] DEBUG: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: blending LoRA from ../models/lora/sdxl-lcm-turbo-mix-euler-a with weight of 1.0                                                                                      
[2023-12-03 22:17:24,375] DEBUG: MainProcess onnx-web health onnx_web.worker.pool: recycling worker pool                                                                                                                                                                
[2023-12-03 22:17:24,375] DEBUG: MainProcess onnx-web health onnx_web.worker.pool: worker 1374168 for device cuda has run 1 jobs and is still alive                                                                                                                     
[2023-12-03 22:17:24,375] DEBUG: MainProcess onnx-web health onnx_web.worker.pool: logger worker is running                                                                                                                                                             
[2023-12-03 22:17:24,375] DEBUG: MainProcess onnx-web health onnx_web.worker.pool: progress worker is running                                                                                                                                                           
[2023-12-03 22:17:24,375] DEBUG: MainProcess onnx-web health onnx_web.worker.pool: worker pool recycled                                                                                                                                                                 
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_1_0_emb_layers_1                                                                                                                     
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_1_0_in_layers_2                                                                                                                      
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_1_0_out_layers_3
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_2_0_emb_layers_1                               
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_2_0_in_layers_2                                                                 
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_2_0_out_layers_3
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_3_0_op
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_4_0_emb_layers_1            
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_4_0_in_layers_2
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_4_0_out_layers_3                                                                                                                     
[2023-12-03 22:17:31,305] WARNING: onnx-web worker: cuda MainThread onnx_web.convert.diffusion.lora: new XL key type: input_blocks_4_0_skip_connection                                                             
[2023-12-03 22:17:31,308] ERROR: onnx-web worker: cuda MainThread onnx_web.chain.pipeline: error while running stage pipeline, 9 retries left                                                                                                                           
Traceback (most recent call last):                                                                                                                                                                                                                                      
  File "/opt/onnx-web/api/onnx_web/chain/pipeline.py", line 223, in __call__                                                                                                                                                                                            
    stage_result = stage_pipe.run(                                                                                                                                                                                                                                      
  File "/opt/onnx-web/api/onnx_web/chain/source_txt2img.py", line 106, in run
    pipe = load_pipeline(
  File "/opt/onnx-web/api/onnx_web/diffusers/load.py", line 207, in load_pipeline
    unet_components = load_unet(server, device, model, loras, unet_type, params)
  File "/opt/onnx-web/api/onnx_web/diffusers/load.py", line 480, in load_unet
    unet = blend_loras(
  File "/opt/onnx-web/api/onnx_web/convert/diffusion/lora.py", line 487, in blend_loras
    blended = fix_xl_names(blended, nodes)
  File "/opt/onnx-web/api/onnx_web/convert/diffusion/lora.py", line 140, in fix_xl_names
    match = next(
StopIteration

These are a new format of keys and not recognized by the code yet. It looks like they have most of the necessary indices, but it looks like there are some new nodes in there.

@ssube ssube added status/new issues that have not been confirmed yet type/bug broken features scope/api model/lora labels Dec 3, 2023
@ssube ssube added this to the v0.12 milestone Dec 25, 2023
@ssube ssube added status/planned issues that have been planned but not started and removed status/new issues that have not been confirmed yet labels Dec 25, 2023
@ssube ssube modified the milestones: v0.12, v0.13 Dec 31, 2023
@ssube ssube modified the milestones: v0.13, v0.14 Jan 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
model/lora scope/api status/planned issues that have been planned but not started type/bug broken features
Projects
None yet
Development

No branches or pull requests

1 participant