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")
https://huggingface.co/intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound/resolve/main/utils/__pycache__/__init__.cpython-311.pyc
hf download hf://intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound/utils/__pycache__/__init__.cpython-311.pyc
curl -L -o __init__.cpython-311.pyc https://huggingface.co/intel-ai/HunyuanImage-3.0-Instruct-Distil-MXFP4-Mixed-AutoRound/resolve/main/utils/__pycache__/__init__.cpython-311.pyc
