fast-stable-diffusion icon indicating copy to clipboard operation
fast-stable-diffusion copied to clipboard

I cannot use the recent 1.5 model in dreambooth

Open TOUGH-manemobu opened this issue 1 year ago • 0 comments

Please note that some sentences may be incorrect because we use translation software.

I cannot use the recent 1.5 model in dreambooth.

betterPonyDiffusionV6_v6.safetensors https://civitai.com/models/544876/better-pony-diffusion-v6-for-sd-15 This model is ponydiffusionv6 for 1.5. It would be great if you could support dreambooth. ―――――――――― 1.5 Detected Converting to Diffusers ... Traceback (most recent call last): File "/content/diffusers/scripts/convert_original_stable_diffusion_to_diffusers.py", line 128, in pipe = download_from_original_stable_diffusion_ckpt( File "/usr/local/lib/python3.10/dist-packages/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py", line 1318, in download_from_original_stable_diffusion_ckpt text_model = convert_ldm_clip_checkpoint(checkpoint) File "/usr/local/lib/python3.10/dist-packages/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py", line 765, in convert_ldm_clip_checkpoint text_model.load_state_dict(text_model_dict) File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 2584, in load_state_dict raise RuntimeError( RuntimeError: Error(s) in loading state_dict for CLIPTextModel: Missing key(s) in state_dict: "text_model.embeddings.position_ids". rm: cannot remove '/content/stable-diffusion-custom': No such file or directory Conversion error Conversion error ――――――――――

TOUGH-manemobu avatar Dec 10 '24 01:12 TOUGH-manemobu