Instructions to use amd/stable-diffusion-xl-1.0_io32_amdgpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use amd/stable-diffusion-xl-1.0_io32_amdgpu with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("amd/stable-diffusion-xl-1.0_io32_amdgpu", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download model_index.json from amd/stable-diffusion-xl-1.0_io32_amdgpu: direct link, hf CLI and curl.
- Browser
- Download file 899 Bytes
-
https://huggingface.co/amd/stable-diffusion-xl-1.0_io32_amdgpu/resolve/main/model_index.json
- Command line
-
hf download hf://amd/stable-diffusion-xl-1.0_io32_amdgpu/model_index.json
-
curl -L -o model_index.json https://huggingface.co/amd/stable-diffusion-xl-1.0_io32_amdgpu/resolve/main/model_index.json
899 Bytes
| { | |
| "_class_name": "ORTStableDiffusionXLPipeline", | |
| "_diffusers_version": "0.27.2", | |
| "_name_or_path": "C:\\Users\\ml-admin\\Desktop\\Owen\\Procyon\\Procyon\\sianos\\models\\pytorch\\stabilityai\\stable-diffusion-xl-base-1.0", | |
| "feature_extractor": [ | |
| null, | |
| null | |
| ], | |
| "force_zeros_for_empty_prompt": true, | |
| "image_encoder": [ | |
| null, | |
| null | |
| ], | |
| "scheduler": [ | |
| "diffusers", | |
| "EulerDiscreteScheduler" | |
| ], | |
| "text_encoder": [ | |
| "diffusers", | |
| "OnnxRuntimeModel" | |
| ], | |
| "text_encoder_2": [ | |
| "diffusers", | |
| "OnnxRuntimeModel" | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "CLIPTokenizer" | |
| ], | |
| "tokenizer_2": [ | |
| "transformers", | |
| "CLIPTokenizer" | |
| ], | |
| "unet": [ | |
| "diffusers", | |
| "OnnxRuntimeModel" | |
| ], | |
| "vae_decoder": [ | |
| "diffusers", | |
| "OnnxRuntimeModel" | |
| ], | |
| "vae_encoder": [ | |
| null, | |
| null | |
| ] | |
| } | |