AI 又一次颠覆游戏世界——揭秘腾讯开源的 Hunyuan-GameCraft

git clone https://github.com/Tencent-Hunyuan/Hunyuan-GameCraft-1.0.git
cd Hunyuan-GameCraft-1.0

# 1. Create conda environment
conda create -n HYGameCraft python==3.10

# 2. Activate the environment
conda activate HYGameCraft

# 3. Install PyTorch and other dependencies using conda
conda install pytorch==2.5.1 torchvision==0.20.0 torchaudio==2.5.1 pytorch-cuda=12.4 -c pytorch -c nvidia

# 4. Install pip dependencies
python -m pip install -r requirements.txt
# 5. Install flash attention v2 for acceleration (requires CUDA 11.8 or above)
python -m pip install ninja
python -m pip install git+https://github.com/Dao-AILab/flash-attention.git@v2.6.3

# For CUDA 12.4 (updated to avoid float point exception)
docker pull hunyuanvideo/hunyuanvideo:cuda_12
docker run -itd --gpus all --init --net=host --uts=host --ipc=host --name hunyuanvideo --security-opt=seccomp=unconfined --ulimit=stack=67108864 --ulimit=memlock=-1 --privileged hunyuanvideo/hunyuanvideo:cuda_12
pip install diffusers==0.34.0 transformers==4.54.1

#!/bin/bash
JOBS_DIR=$(dirname $(dirname "$0"))
export PYTHONPATH=${JOBS_DIR}:$PYTHONPATH
export MODEL_BASE="weights/stdmodels"
checkpoint_path="weights/gamecraft_models/mp_rank_00_model_states.pt"

current_time=$(date "+%Y.%m.%d-%H.%M.%S")
modelname='Tencent_hunyuanGameCraft_720P'

torchrun --nnodes=1 --nproc_per_node=8 --master_port 29605 hymm_sp/sample_batch.py \
    --image-path "asset/village.png" \
    --prompt "A charming medieval village with cobblestone streets, thatched-roof houses, and vibrant flower gardens under a bright blue sky." \
    --add-pos-prompt "Realistic, High-quality." \
    --add-neg-prompt "overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion, blurring, text, subtitles, static, picture, black border." \
    --ckpt ${checkpoint_path} \
    --video-size 704 1216 \
    --cfg-scale 2.0 \
    --image-start \
    --action-list w s d a \
    --action-speed-list 0.2 0.2 0.2 0.2 \
    --seed 250160 \
    --infer-steps 50 \
    --flow-shift-eval-video 5.0 \
    --save-path './results/'

git clone https://github.com/thu-ml/SageAttention.git
cd SageAttention 
python setup.py install  # or pip install -e .

#!/bin/bash
JOBS_DIR=$(dirname $(dirname "$0"))
export PYTHONPATH=${JOBS_DIR}:$PYTHONPATH
export MODEL_BASE="weights/stdmodels"
checkpoint_path="weights/gamecraft_models/mp_rank_00_model_states_distill.pt"

current_time=$(date "+%Y.%m.%d-%H.%M.%S")
modelname='Tencent_hunyuanGameCraft_720P'

torchrun --nnodes=1 --nproc_per_node=8 --master_port 29605 hymm_sp/sample_batch.py \
    --image-path "asset/village.png" \
    --prompt "A charming medieval village with cobblestone streets, thatched-roof houses, and vibrant flower gardens under a bright blue sky." \
    --add-neg-prompt "overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion, blurring, text, subtitles, static, picture, black border." \
    --ckpt ${checkpoint_path} \
    --video-size 704 1216 \
    --cfg-scale 1.0 \
    --image-start \
    --action-list w s d a \
    --action-speed-list 0.2 0.2 0.2 0.2 \
    --seed 250160 \
    --infer-steps 8 \
    --use-fp8 \
    --flow-shift-eval-video 5.0 \
    --save-path './results_distill/'