Image-to-Image
Transformers
Safetensors
hunyuan_image_3_moe
text-generation
auto-round
mxfp4
custom_code
8-bit precision
Instructions to use intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-image" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-image", model="intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download images/grid_ar_ditonly.png from intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound: direct link, hf CLI and curl.
- Browser
- Download file 734 kB
-
https://huggingface.co/intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound/resolve/main/images/grid_ar_ditonly.png
- Command line
-
hf download hf://intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound/images/grid_ar_ditonly.png
-
curl -L -o grid_ar_ditonly.png https://huggingface.co/intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound/resolve/main/images/grid_ar_ditonly.png
734 kB

- Xet hash:
- 9851df5960fbd938d32296cf83b8307db67ad70baedfdef6413f747cf07c05cd
- Size of remote file:
- 734 kB
- SHA256:
- 1ded99a246dbc66b57f1ad127f3f70773d6bb7264fc3d526616d8a25dda8c868
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.