Hello! Who can explain how to take a safetensors file (for example, from civitai) and integrate it as a model for diffusers? The from_single_file() method does not work on any version of diffusers (conversion error). It is also completely unclear how to transfer this safetensors file to Hugging Face in a format understandable to diffusers to load it via the from_pretrained method.
Convert error example:
Traceback (most recent call last):
File "/src/scripts/download-weights", line 25, in <module>
pipe = StableDiffusionPipeline.from_single_file("./zhanche-v100.safetensors", use_safetensors=True, cache_dir=MODEL_CACHE)
File "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/diffusers/loaders/single_file.py", line 261, in from_single_file
pipe = download_from_original_stable_diffusion_ckpt(
File "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py", line 1436, in download_from_original_stable_diffusion_ckpt
converted_unet_checkpoint = convert_ldm_unet_checkpoint(
File "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py", line 426, in convert_ldm_unet_checkpoint
new_checkpoint["time_embedding.linear_1.weight"] = unet_state_dict["time_embed.0.weight"]
KeyError: 'time_embed.0.weight'
ⅹ exit status 1