lora-inference

lora-inference copied to clipboard

Steps:

• Get link from https://civitai.com/models/4361/olivia-diffusion
• Inference with https://replicate.com/cloneofsimo/lora and a style trained by https://replicate.com/cloneofsimo/lora-training

Actual: Error 'NoneType' object is not iterable Expect: can use civitai

This is known issue since LoRA format is different. We will work on this in the future. Thanks!

Any update on this @cloneofsimo ? It would be amazing to use those loras.

Once supported, this will be great. Watch for progress.

@cloneofsimo version 0.17 of the diffusers library now handle the A1111 / kohya_ss LoRA format. That should help updating this cog? https://github.com/huggingface/diffusers/releases/tag/v0.17.0

any updates?

I have not used this, but check this out https://replicate.com/fofr/any-comfyui-workflow

I found a create solution https://github.com/lucataco/cog-civitai-sdxl-template Worked for me, created 8 containers

hmm suppose you simply want to convert the civitai .safetensors to replicate's lora tar: which contain the safetenwsors and also embeddings.pti, special_params.json

hmm suppose you simply want to convert the civitai .safetensors to replicate's lora tar: which contain the safetenwsors and also embeddings.pti, special_params.json

When downloading any .safetensors file from civitai how do i get the embeddings.pti and special_params.json so that I could create the tar to use in replicate?