stabilityai/stable-diffusion-3.5-medium-amdnpu

1---2license: other3license_name: stabilityai-ai-community4license_link: LICENSE5tags:6- text-to-image7- stable-diffusion8- diffusers9inference: true10extra_gated_prompt: >-11  By clicking "Agree", you agree to the [License12  Agreement](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium-amdnpu/blob/main/LICENSE)13  and acknowledge Stability AI's [Privacy14  Policy](https://stability.ai/privacy-policy).15extra_gated_fields:16  Name: text17  Email: text18  Country: country19  Organization or Affiliation: text20  Receive email updates and promotions on Stability AI products, services, and research?:21    type: select22    options:23    - 'Yes'24    - 'No'25  What do you intend to use the model for?: 26    type: select27    options:28    - Research29    - Personal use30    - Creative Professional31    - Startup32    - Enterprise33  I agree to the License Agreement and acknowledge Stability AI's Privacy Policy: checkbox34 35language:36- en37pipeline_tag: text-to-image38---39 40# 🚀 Stable Diffusion 3.5 Medium on AMD NPU41 42"Stable Diffusion 3.5 Medium is an improved version of SD3 Medium, featuring better prompt adherence, better generation quality, and more diverse outputs. SD3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved image quality, typography, and prompt understanding." ([stabilityai/stable-diffusion-3.5-medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium))43 44This version of the model has been optimized to run on AMD NPUs.45 46For more information, refer to the original model card under [stabilityai/stable-diffusion-3.5-medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium).47 48## Model Details49 50| Model Details | Description |51| ----------- | ----------- | 52| Person or organization developing model | [AMD](https://hf.co/amd) | 53| Original model authors | [Stability AI](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium) | 54| Model date | February 2026 | 55| Model version | 1.8.0 | 56| Model type | Diffusion-based text-to-image generation model | 57| Information about training algorithms, parameters, fairness constraints or other applied approaches, and features | This is a model that can be used to generate and modify images based on text prompts. | 58| License | [Stability AI Community](LICENSE) |59| Where to send questions or comments about the model | [Community Tab](https://hf.co/amd/stable-diffusion-3.5-medium-amdnpu/discussions) and [AMD Developer Community Discord](https://discord.gg/amd-dev) |60 61## ⚡ Intended Use62 63#### Getting Started64 65To get started with this model, visit [github.com/amd/sd-sandbox](https://github.com/amd/sd-sandbox). 66 67## ⚓ Ethical Considerations68 69AMD 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](https://www.amd.com/en/corporate/corporate-responsibility/ethics-and-compliance.html) page.70 71## ⚠️ Caveats and Recommendations72 73Please visit the original model card for more details: [stabilityai/stable-diffusion-3.5-medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium).