Please refer to load_quantized_model.py script, on the buttom I had Comment:

replace:

self.model = HunyuanImage3ForCausalMM.from_pretrained(args.model_id, **kwargs)

with:

self.model = load_quantized_hi3_m1(args.model_id)

or with:

self.model = load_quantized_hi3_m2(args.model_id)

please accroding to the comment content to modeify app/pipeline.py script "self.model = HunyuanImage3ForCausalMM.from_pretrained( )" line...

Please refer to load_quantized_model.py script, on the buttom I had Comment:

replace:

self.model = HunyuanImage3ForCausalMM.from_pretrained(args.model_id, **kwargs)

with:

self.model = load_quantized_hi3_m1(args.model_id)

or with:

self.model = load_quantized_hi3_m2(args.model_id)

please accroding to the comment content to modeify app/pipeline.py script "self.model = HunyuanImage3ForCausalMM.from_pretrained( )" line...

Thanks!

After this, how?
Run:

Set your model path

export MODEL_ID="path/to/your/model"

Optional: Configure GPU usage (default: 0,1,2,3)

export GPUS="0,1,2,3"

Optional: Configure host and port (default: 0.0.0.0:443)

export HOST="0.0.0.0"
export PORT="443"

sh run_app.sh