Add what's new section to model card
Browse files
README.md
CHANGED
|
@@ -12,6 +12,15 @@ This is a port to Diffuser from original [SD Webui's Layer Diffusion](https://gi
|
|
| 12 |
|
| 13 |
|
| 14 |
Paper: [Transparent Image Layer Diffusion using Latent Transparency](https://arxiv.org/abs/2402.17113)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## Quickstart
|
| 16 |
|
| 17 |
Generate transparent image with SD1.5 models. In this example, we will use [digiplay/Juggernaut_final](https://huggingface.co/digiplay/Juggernaut_final) as the base model
|
|
|
|
| 12 |
|
| 13 |
|
| 14 |
Paper: [Transparent Image Layer Diffusion using Latent Transparency](https://arxiv.org/abs/2402.17113)
|
| 15 |
+
|
| 16 |
+
## What's new
|
| 17 |
+
|
| 18 |
+
- Added Diffusers-ready SDXL LayerDiffuse conditional weights for foreground-to-blending, background-to-blending, foreground-and-blend-to-background, and background-and-blend-to-foreground workflows.
|
| 19 |
+
- New remote weights: `diffuser_layer_xl_fg2ble.safetensors`, `diffuser_layer_xl_bg2ble.safetensors`, `diffuser_layer_xl_fgble2bg.safetensors`, and `diffuser_layer_xl_bgble2fg.safetensors`.
|
| 20 |
+
- The GitHub examples load these weights from this Hugging Face repo through the local HF cache by default.
|
| 21 |
+
- SDXL Forge weight conversion is now consolidated in `scripts/convert_xl_layerdiffuse.py` with `--mode fg2ble|bg2ble|fgble2bg|bgble2fg`.
|
| 22 |
+
- Demo scripts now expose CLI options for model, prompt, seed, output path, `--variant`, and `--cpu-offload`; run any script with `--help` for details.
|
| 23 |
+
|
| 24 |
## Quickstart
|
| 25 |
|
| 26 |
Generate transparent image with SD1.5 models. In this example, we will use [digiplay/Juggernaut_final](https://huggingface.co/digiplay/Juggernaut_final) as the base model
|