# lllyasviel/sd-forge-layerdiffuse

[WIP] Layer Diffusion for WebUI (via Forge)

Repository: https://github.com/lllyasviel/sd-forge-layerdiffuse
Canonical: https://ross.abutalabs.com/products/sd-forge-layerdiffuse
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-08-30T22:05:11+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 65
- inputs: {"age_days": 915, "days_push": 733, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4116, forks 352 (observed 2026-08-28T04:08:35.861948+00:00)

## What it is
A Stable Diffusion WebUI (Forge) extension implementing Layer Diffusion to generate transparent images and separate foreground/background layers natively via a transparent latent space. It provides SDXL-based models for transparent generation, layer decomposition, and composition workflows.

## Use cases
- generate transparent PNG images with stable diffusion
- remove image backgrounds natively during diffusion
- split an image into foreground and background layers
- generate foreground layers conditioned on a background
- create semi-transparent effects like glass and glow in AI images

## When to choose
- you use SD WebUI Forge and need native transparent image generation
- you want layer separation (foreground/background) rather than post-hoc background removal
- you need fine details like fur, hair, or transparency preserved in generated images

## When to avoid
- you use ComfyUI or another UI instead of Forge
- you need production-stable tooling - the project is marked WIP
- you work with models other than SDXL

## Facets
- artifact type: plugin
- maturity: active
- function: image-processing, stable-diffusion, machine-learning
- domain: image-processing, artificial-intelligence, graphics
- platform: python, cross-platform
- tags: stable-diffusion, sd-webui-extension, transparent-images, layer-generation, sdxl, forge, gpu

## Member repositories
- lllyasviel/sd-forge-layerdiffuse (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:35.861948+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:09.373677+00:00, confidence not recorded.
  - readme: https://github.com/lllyasviel/sd-forge-layerdiffuse (fetched 2026-08-28T04:08:35.861948+00:00, sha ae04da24300f)
- Data as of 2026-08-30T08:39:29.467469+00:00.