This repo is a Flux version implementation of LayerDiffuse (LayerDiffuse).
We train a new transparent vae to adapt to Flux and train a lora to finetune Flux to generate transparent images.
 |
 |
 |
 |
 |
 |
 |
|---|
- Clone this repository.
git clone ...
cd LayerDiffuse-Flux- download weights
huggingface-cli download --resume-download --local-dir ./models RedAIGC/Flux-version-LayerDiffuse python demo_t2i.py --ckpt_path /your/path/to/FLUX.1 dev| Examples: top to bottom: flux, flux-layer(ours), sdxl, sdxl-layer(LayerDiffuse) |
|---|
 |
 |
 |
 |
 |
python demo_i2i.py --ckpt_path /your/path/to/FLUX.1 dev --image "./imgs/causal_cut.png" Prompt: "a handsome man with curly hair, high quality"
Strength: 0.9
| Input (Transparent image) | Output (Transparent image) |
|---|---|
 |
 |
Thanks lllyasviel for their great work LayerDiffuse
If you have any questions about the code, please do not hesitate to contact us!
Email: [email protected], [email protected]