Instructions to use XLabs-AI/flux-RealismLora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use XLabs-AI/flux-RealismLora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("XLabs-AI/flux-RealismLora") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Use with Diffusers
#9
by HaileyStorm - opened
Do you know how to use this with the diffusers library? Using pipeline.load_lora_weights(), with or without fuse_lora(), "works" (no errors) but does not produce any effect.
Hi!
Loras from XLabs-AI are not supported in the Diffusers library, so they will not work.
This comment has been hidden
you can convert the lora weights yourself to diffusers' format.
You can try our converted checkpoint here: https://huggingface.co/mit-han-lab/FLUX.1-dev-LoRA-Collections/resolve/main/realism.safetensors
I think currently, diffusers can directly load it.