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!