Ryzen-AI-1.8.0 — SD Models
Collection
Stable Diffusion (SD) and image generation models for AMD NPU • 17 items • Updated • 3
🚀 Segmind Stable Diffusion 1B (SSD-1B) on AMD AI PC NPU
SSD-1B is a distilled, 50% smaller version of Stable Diffusion XL (SDXL) that offers faster inference while maintaining high-quality text-to-image generation. For more information, please see the technical report.
More details about this model can be found on the original Hugging Face model card: segmind/SSD-1B.
This model repo contains the optimized ONNX models required to run the image generation pipeline for SSD-1B on AMD NPUs.
Model Details
The folder structure is organized to mirror the main components of the SDXL-style diffusion pipeline (scheduler, text encoders, tokenizers, UNet, and VAE decoder).
├─ scheduler/
├─ text_encoder/
├─ text_encoder_2/
├─ tokenizer/
├─ tokenizer_2/
├─ unet/
└─ vae_decoder/
The scheduler folder contains the scheduler configuration (timesteps, betas, alphas, etc.) used during the diffusion sampling process.
The text_encoder and text_encoder_2 folders contain the text encoder models used to convert the input prompt into conditioning embeddings for the diffusion model.
The tokenizer and tokenizer_2 folders contain the tokenizer configuration and vocabulary files required to preprocess text prompts before they are fed to the text encoders.
The unet folder contains the UNet model used in the diffusion process. The UNet is exported and structured specifically to leverage the AMD NPU accelerator for the denoising steps.
The vae_decoder folder contains the VAE decoder model used to map latent representations back to the image space. The VAE decoder is also structured to make use of the NPU accelerator for efficient image reconstruction.
Note: UNet and VAE decoder models are optimized and structured to run on AMD NPUs. The other components (text encoders, tokenizers and scheduler) are shared between GPU and NPU pipelines, but are provided here for completeness.
| Model Details | Description |
|---|---|
| Person or organization developing model | Benjamin Consolvo (AMD), makn87amd (AMD) |
| Original model authors | Yatharth Gupta, Vishnu Jaddipal (Segmind) |
| Model date | April 2026 |
| Model version | 1.8.0 |
| Model type | Distilled SDXL text-to-image generation model |
| Information about training algorithms, parameters, fairness constraints or other applied approaches, and features | 1.3B-parameter model distilled from SDXL using progressive knowledge distillation. Distilled from stabilityai/stable-diffusion-xl-base-1.0. |
| License | Apache 2.0 — see segmind/SSD-1B |
| Where to send questions or comments about the model | Community Tab and AMD Developer Community Discord |
⚡ Intended Use
Getting Started
To get started with this model, visit github.com/amd/sd-sandbox.
⚓ Ethical Considerations
AMD is committed to conducting our business in a fair, ethical and honest manner and in compliance with all applicable laws, rules and regulations. You can find out more at the AMD Ethics and Compliance page.
⚠️ Caveats and Recommendations
Please visit the original model card for more details on limitations and bias: segmind/SSD-1B.
📌 Citation Details
@misc{gupta2024progressive,
title={Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss},
author={Yatharth Gupta and Vishnu V. Jaddipal and Harish Prabhala and Sayak Paul and Patrick Von Platen},
year={2024},
eprint={2401.02677},
archivePrefix={arXiv},
primaryClass={cs.CV}
}