multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
e38ae43 verified
|
Raw History Blame Contribute Delete
1.73 kB
---
title: Sample-Aligned Decoders
emoji: 🎨
colorFrom: red
colorTo: green
sdk: gradio
sdk_version: 6.32.0
app_file: app.py
short_description: Drop-in fine-tuned VAE decoders for latent generators
python_version: "3.12"
startup_duration_timeout: 30m
---
# Sample-Aligned Decoders (SAD)
**Paper**: [Sample-Aligned Decoders for Latent Generative Models](https://huggingface.co/papers/2611.22458) ·
**Code**: [github.com/torpedo2003/SAD](https://github.com/torpedo2003/SAD) ·
**Decoders**: [huggingface.co/torpedo2003/SAD](https://huggingface.co/torpedo2003/SAD)
SAD is a decoder post-training framework for latent generative models: fine-tune **only the VAE
decoder** on latents sampled from the frozen generator (~1 GPU-hour). The decoder keeps its
architecture, so it is a **drop-in swap with zero extra inference cost** — it corrects color cast,
exposure and texture while leaving content and layout untouched.
## What this demo does
It runs **PixArt-α 256px** with the authors' exact sampler recipe (20 DPM-Solver++ steps,
guidance 4.5 — the configuration the `pixart-alpha-256/sad-gan` decoder was trained for):
1. one prompt → **one latent** from the frozen PixArt-α base model;
2. that same latent is decoded twice — with the **original SD-VAE decoder D₀** and with the **SAD decoder**;
3. the **|SAD − D₀| heatmap** (paper colormap) shows where the decoder changed the image.
Because the latent is identical, every difference between the two images is purely the decoder.
## Example prompts
The examples are the official PixArt-α prompts from the
[PixArt-XL-2-256x256](https://huggingface.co/PixArt-alpha/PixArt-XL-2-256x256) model repo, sampled
with the same 20-step / cfg-4.5 recipe used here.