Spaces:
Running on Zero
Running on Zero
|
Download README.md from hugging-apps/rads-diffusion-steering: direct link, hf CLI and curl.
- Browser
- Download file 2.2 kB
-
https://huggingface.co/spaces/hugging-apps/rads-diffusion-steering/resolve/main/README.md
- Command line
-
hf download hf://spaces/hugging-apps/rads-diffusion-steering/README.md
-
curl -L -o README.md https://huggingface.co/spaces/hugging-apps/rads-diffusion-steering/resolve/main/README.md
2.2 kB
| title: RADS — Steering Away from Memorization in Text-to-Image Diffusion | |
| emoji: 🧭 | |
| colorFrom: green | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: 6.32.0 | |
| app_file: app.py | |
| python_version: "3.12" | |
| startup_duration_timeout: 30m | |
| short_description: Steer SD v1.4 away from memorization at inference time | |
| # RADS: Reachability-Constrained Reinforcement Learning for Diffusion Steering | |
| Demo for the paper **"Steering Away from Memorization: Reachability-Constrained | |
| Reinforcement Learning for Text-to-Image Diffusion"** ([HF paper page](https://huggingface.co/papers/2603.00140), | |
| [project page](https://s-karnik.github.io/rads-memorization-project-page)). | |
| ## What this demo does | |
| RADS is an **inference-time** steering controller for text-to-image diffusion. | |
| A Soft Actor-Critic policy — trained offline against a reachability-based | |
| safety critic — perturbs the prompt's caption embedding in a learned 64-d | |
| latent space at every denoising step, keeping generation inside a safe | |
| (Non-Memorizing) region of the diffusion trajectory. The diffusion backbone | |
| (Stable Diffusion v1.4, DDIM, T=50, g=7.5 — the paper's evaluation setting) | |
| is **never modified**. | |
| For the same prompt and the **same initial latent**, this demo generates: | |
| - **Left:** the plain SD v1.4 baseline (steering strength 0) | |
| - **Right:** the RADS-steered image (steering strength 1, the paper default) | |
| Both images come from an identical seed, so every visible difference is caused | |
| by steering alone. Example prompts are memorization-prone prompts from the | |
| paper's evaluation sets (Webster et al. 2023 and MemBench). | |
| ## Checkpoints | |
| SAC agent checkpoints (encoder + actor, training seeds 41–45) and the CLIP | |
| caption-embedding autoencoder are loaded from | |
| [`S-Karnik/rads-model-checkpoints`](https://huggingface.co/S-Karnik/rads-model-checkpoints). | |
| The official implementation lives at | |
| [`S-Karnik/rads-paper-repo`](https://github.com/S-Karnik/rads-paper-repo) (MIT). | |
| ## Citation | |
| ```bibtex | |
| @inproceedings{karnik2026rads, | |
| title = {Steering Away from Memorization: Reachability-Constrained | |
| Reinforcement Learning for Text-to-Image Diffusion}, | |
| author = {Karnik, Shreyas and others}, | |
| year = {2026} | |
| } | |
| ``` | |