Stable Diffusion#
Ryzen AI 1.9.0 provides preview demos of Stable Diffusion image-generation pipelines. The demos cover Image-to-Image (ControlNet: Canny, Pose, Tile, Depth; plus Segmind-Vega i2i without ControlNet) and Text-to-Image for SD1.5, SD-Turbo, SDXL-base, SDXL-Turbo, Segmind-Vega, DreamShaper XL Lightning, SSD-1B, Playground v2.5, FLUX.1-Schnell, FLUX.2-klein-4B, SD3.0, and SD3.5, with inpainting where noted for SD3.0.
Models are fetched from Hugging Face on first use (see Installation Instructions for Ryzen AI and driver setup). SD3.0 and SD3.5 models require Hugging Face authentication and might also require acceptance of the model license before they can be downloaded.
Installation Steps#
Ensure the latest version of Ryzen AI and NPU drivers are installed. See Installation Instructions.
The GenAI-SD folder is located in the RyzenAI installation tree. Navigate to the folder and run the following command:
$env:RYZEN_AI_INSTALLATION_PATH = "C:\Program Files\RyzenAI\ryzen-ai-1.9.0" & "$env:RYZEN_AI_INSTALLATION_PATH\Scripts\Activate.ps1" cd "$env:RYZEN_AI_INSTALLATION_PATH\GenAI-SD"
Models are downloaded from Hugging Face on first use and cached under
GenAI-SD\modelsor$env:RYZENAI_GENAI_SD_MODELS_ROOT. See supported-models for the full list; primary entry points include:
Supported models#
The following summarizes default application mode, typical resolution /
dynamic-resolution (DynRes) notes, and the recommended Hugging Face model_id on
AMD NPU-tuned repos.
Notes |
Model |
App |
Default resolution / DynRes |
|
|---|---|---|---|---|
SD1.5 |
t2i |
512x512 |
|
|
New |
SD1.5 |
i2i-canny |
512x512 |
|
SD-Turbo |
t2i |
512x512 |
|
|
SDXL-Turbo |
t2i |
512x512, 5x DynRes |
|
|
SDXL-base |
t2i |
1024x1024, 20x DynRes |
|
|
Segmind-Vega |
t2i / i2i |
1024x1024 |
|
|
New |
DreamShaper XL Lightning |
t2i |
1024x1024, 20x DynRes |
|
New |
SSD-1B |
t2i |
1024x1024, 20x DynRes |
|
New |
Playground v2.5 |
t2i |
1024x1024, 20x DynRes |
|
New |
FLUX.1-Schnell |
t2i |
1024x1024, 20x DynRes |
|
New |
FLUX.2-klein-4B |
t2i |
1024x1024 |
|
SD3.0 |
t2i / ControlNet / Depth / Canny / Pose / Tile |
512x512 (t2i default), 20x DynRes where applicable |
|
|
New |
SD3.0 |
i2i-inpainting |
1024x1024 |
|
SD3.5 |
t2i / ControlNet |
512x512 (t2i default), 20x DynRes where applicable |
|
|
SD3.5-ControlNet (Canny) |
i2i-canny |
512x512, 20x DynRes |
Uses SD3.5 AMD weights plus SD3.0 Canny ControlNet assets (see below) |
In the Supported models table, the DynRes column counts how many dynamic-resolution presets a pipeline exposes (for example 5x or 20x). The following material spells out which width x height pairs are in scope.
Dynamic resolution (DynRes)
Original dynamic-resolution requirements
These are the classic fixed pairs (per model class) before the expanded preset grid.
DynRes 5x: 512x512, 288x512, 512x288, 384x512, 512x384.
DynRes 20x:
Aspect (WxH) |
Base 512x512 |
Base 640x640 |
Base 768x768 |
Base 1024x1024 |
|---|---|---|---|---|
1:1 |
512x512 |
640x640 |
768x768 |
1024x1024 |
4:3 |
512x384 |
640x480 |
768x576 |
1024x768 |
3:4 |
384x512 |
480x640 |
576x768 |
768x1024 |
16:9 |
512x288 |
640x384 |
768x448 |
1024x576 |
9:16 |
288x512 |
384x640 |
448x768 |
576x1024 |
Public model pages follow the Hugging Face model license (HF LIC) for each repo.
SD3.5 Canny ControlNet setup: copy the SD3.0 Canny ControlNet files into the SD3.5
model layout as required by your GenAI-SD tree (per release notes), then run the Canny
example with --model_id amd/stable-diffusion-3.5-medium-amdnpu.
Deploy Models on NPU#
This page elaborates on running Stable Diffusion Models on NPU: Running Models on NPU