ONNX Model Zoo

amd/sdxl-turbo-amdnpu

By amd · ↓ 0 · ♥ 2 · Updated 2026-02-24

What's in this repo

This page lists the files in amd/sdxl-turbo-amdnpu, including replaced.onnx and more.

  • 2 ONNX models (.onnx files)
  • 32 files, including 13 .json, 4 .txt, 2 .safetensors, 2 .ctrlpkt, 2 .fconst, 2 .state
  • Last updated 2026-02-24

ONNX files

File Size Download
unet/dd/replaced.onnx — Download
vae_decoder/dd/replaced.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README


language: en tags:

  • stable-diffusion pipeline_tag: text-to-image license: other license_name: stabilityai-ai-community license_link: LICENSE

🚀 SDXL-Turbo on AMD NPU

"SDXL-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation" (stabilityai/sdxl-turbo).

This version of the model has been optimized to run on AMD NPUs.

For more information, refer to the original model card under stabilityai/sdxl-turbo.

Model Details

Model Details Description
Person or organization developing model AMD
Original model authors Stability AI
Model date January 2026
Model version 1.7.1
Model type Diffusion-based text-to-image generation model
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.
License Stability AI Community
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: stabilityai/sdxl-turbo.

Model info

onnx safetensors stable-diffusion text-to-image en license:other region:us
↓ 0 ♥ 2

Created: 2026-01-23

Updated: 2026-02-24

View on Hugging Face

Files (32)

.gitattributes
LICENSE
README.md
scheduler/scheduler_config.json
text_encoder/config.json
text_encoder/model.safetensors
text_encoder_2/config.json
text_encoder_2/model.safetensors
tokenizer/merges.txt
tokenizer/special_tokens_map.json
tokenizer/tokenizer_config.json
tokenizer/vocab.json
tokenizer_2/merges.txt
tokenizer_2/special_tokens_map.json
tokenizer_2/tokenizer_config.json
tokenizer_2/vocab.json
unet/config.json
unet/dd/cache/NhwcConv_0-unetconv_inConv_meta.json
unet/dd/dd_metastate_SD15_Unet_NhwcConv_0-unetconv_inConv.ctrlpkt
unet/dd/dd_metastate_SD15_Unet_NhwcConv_0-unetconv_inConv.fconst
unet/dd/dd_metastate_SD15_Unet_NhwcConv_0-unetconv_inConv.state
unet/dd/dd_metastate_SD15_Unet_NhwcConv_0-unetconv_inConv.super
unet/dd/onnx_report.txt
unet/dd/replaced.onnx ONNX
vae_decoder/config.json
vae_decoder/dd/cache/NhwcConv_0-post_quant_convConv_meta.json
vae_decoder/dd/dd_metastate_Sd15_Decoder_NhwcConv_0-post_quant_convConv.ctrlpkt
vae_decoder/dd/dd_metastate_Sd15_Decoder_NhwcConv_0-post_quant_convConv.fconst
vae_decoder/dd/dd_metastate_Sd15_Decoder_NhwcConv_0-post_quant_convConv.state
vae_decoder/dd/dd_metastate_Sd15_Decoder_NhwcConv_0-post_quant_convConv.super
vae_decoder/dd/onnx_report.txt
vae_decoder/dd/replaced.onnx ONNX

Related models