Support new loras from Flux Authors

[MohamedAliRashad]

I have tried this code:

import torch
from diffusers import AutoPipelineForImage2Image

pipeline = AutoPipelineForImage2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipeline.unload_lora_weights()
pipeline.load_lora_weights("black-forest-labs/FLUX.1-Redux-dev")
pipeline.enable_model_cpu_offload()

and it gave me this error:

ValueError: Invalid LoRA checkpoint.

[ukaprch]

Try something similar to this:

adapter_id = "Shakker-Labs/FLUX.1-dev-LoRA-blended-realistic-illustration"
pipe.load_lora_weights(adapter_id, weight_name="FLUX.1-dev-LoRA-add-details.safetensors")
#optionally:
pipe.fuse_lora(lora_scale=1.0)

[a-r-r-o-w]

We're working on it in #9985 and #9999. Until then this error will be expected but those should be merged soon!

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

[a-r-r-o-w]

Marking as closed because these are now supported. Please let us know if you face any problems regarding this 🤗