Lunmingpei
commented
1 year ago I met the same bug today. I tried to create a new model using NovelAI (animefull-latest.ckpt).
Loading model from checkpoint. Loading checkpoint... Pipeline or config is not set, unable to continue. Restored system models. Allocated: 10.8GB Reserved: 11.0GB
Allocated 10.8/10.8GB Reserved: 11.0/11.0GB
Exception while extracting model: 'state_dict' Error completing request Arguments: ('test', 'animefull-latest.ckpt [e6e8e1fc]', 'ddim', False, '', '', True) {} Traceback (most recent call last): File "E:\stable-diffusion-webui (2)\modules\call_queue.py", line 45, in f res = list(func(*args, *kwargs)) File "E:\stable-diffusion-webui (2)\modules\call_queue.py", line 28, in f res = func(args, **kwargs) File "E:\stable-diffusion-webui (2)\extensions\sd_dreambooth_extension\dreambooth\sd_to_diff.py", line 962, in extract_checkpoint db_config.resolution, \ AttributeError: 'NoneType' object has no attribute 'resolution'
Traceback (most recent call last): File "E:\stable-diffusion-webui (2)\venv\lib\site-packages\gradio\routes.py", line 284, in run_predict output = await app.blocks.process_api( File "E:\stable-diffusion-webui (2)\venv\lib\site-packages\gradio\blocks.py", line 983, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "E:\stable-diffusion-webui (2)\venv\lib\site-packages\gradio\blocks.py", line 913, in postprocess_data if predictions[i] is components._Keywords.FINISHED_ITERATING: IndexError: tuple index out of range Allocated 3.6/10.8GB Reserved: 11.0/11.0GB
Stardust-SJF
patrickmros
d8ahazard
NivaucchuRabuessa
Kindly read this ENTIRE form and fill it out with the requested information. It may seem tedious, but it's even more tedious asking basic questions to ensure I'm not trying to troubleshoot a bug I've already fixed. Help me help you, answer all the questions and follow the steps below before posting.
` Python revision: 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Dreambooth revision: 47cce57fe84f318eba85a1b8c0d9908f0643f1eb and 88cc50ace470580842b519115545b9a08ebe115e SD-WebUI revision: 44c46f0ed395967cd3830dd481a2db759fda5b3b
Checking Dreambooth requirements... [+] bitsandbytes version 0.35.0 installed. [+] diffusers[torch] version 0.10.0.dev0 installed. [+] transformers version 4.21.0 installed. [ ] xformers version 0.0.14.dev0 installed. [ ] torch version 1.12.1+cu116 installed. [ ] torchvision version 0.13.1+cu116 installed. `
Have you read the Readme?
yes
Have you completely restarted the stable-diffusion-webUI, not just reloaded the UI?
yes (many times)
Have you updated Dreambooth to the latest revision?
yes
Have you updated the Stable-Diffusion-WebUI to the latest version?
yes
No, really. Please save us both some trouble and update the SD-WebUI and Extension and restart before posting this. Reply 'OK' Below to acknowledge that you did this.
OK
Describe the bug
Had problems using a self-mixed model with dreambooth. After an update yesterday it worked. Something about state_dict and checkpoint not found. I remember the phrase "Trying something else". Trained a model over night. After the newest update today i have problems with that model again. Looks like the same error with slightly different error message. "Trying something else" is missing now. Maybe "something else" should be used? ;-)
Provide logs
Loading model from checkpoint. Loading checkpoint... Pipeline or config is not set, unable to continue. Exception while extracting model: 'state_dict' Error completing request Arguments: ('test', "mix_model1.ckpt [c19ca25b]", 'ddim', False, '', '', False) {} Traceback (most recent call last): File "J:\sd_06_10_2022\stable-diffusion-webui\modules\call_queue.py", line 45, in f res = list(func(*args, *kwargs)) File "J:\sd_06_10_2022\stable-diffusion-webui\modules\call_queue.py", line 28, in f res = func(args, **kwargs) File "J:\sd_06_10_2022\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\sd_to_diff.py", line 962, in extract_checkpoint db_config.resolution, \ AttributeError: 'NoneType' object has no attribute 'resolution'
Traceback (most recent call last): File "J:\sd_06_10_2022\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 284, in run_predict output = await app.blocks.process_api( File "J:\sd_06_10_2022\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 983, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "J:\sd_06_10_2022\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 913, in postprocess_data if predictions[i] is components._Keywords.FINISHED_ITERATING: IndexError: tuple index out of range
Environment
What OS?
Windows - native
What GPU are you using?
RTX 3060 12 GB VRAM
Screenshots/Config