DGX Spark에서 Cosmos 3 Edge로 이미지를 짧은 영상으로 만들기

python3 -m venv .venv
source .venv/bin/activate
python -m pip install -U huggingface_hub requests
hf auth login
cosmos_cache="${HF_HOME:-$HOME/.cache/huggingface}"
mkdir -p "$cosmos_cache"
docker run --rm --name cosmos3-edge --platform linux/arm64 \
  --runtime nvidia --gpus all --ipc=host \
  -p 127.0.0.1:8000:8000 \
  -v "$cosmos_cache:/root/.cache/huggingface" \
  vllm/vllm-omni:cosmos3 \
  vllm serve nvidia/Cosmos3-Edge --omni --host 0.0.0.0 --port 8000 \
    --init-timeout 1800

source .venv/bin/activate
hf download nvidia/Cosmos3-Edge --include "assets/*" --local-dir Cosmos3-Edge

cd Cosmos3-Edge
python - <<'PY'
import json, mimetypes, requests
from pathlib import Path
prompt = json.load(open('assets/example_i2v_prompt.json'))
negative = json.load(open('assets/negative_prompt.json'))
image = Path('assets/example_i2v_input.jpg')
data = {
    'prompt': json.dumps(prompt),
    'negative_prompt': json.dumps(negative),
    'size': '832x480',
    'num_frames': '121',
    'fps': '24',
    'num_inference_steps': '20',
    'guidance_scale': '6.0',
    'max_sequence_length': '4096',
    'flow_shift': '12.0',
    'seed': '0',
    'extra_params': json.dumps({
        'use_resolution_template': False,
        'use_duration_template': False,
        'guardrails': True,
    }),
}
mime = mimetypes.guess_type(image.name)[0] or 'image/jpeg'
with image.open('rb') as file:
    response = requests.post('http://127.0.0.1:8000/v1/videos/sync', data=data, files={'input_reference': (image.name, file, mime)}, headers={'Accept': 'video/mp4'}, timeout=1800)
response.raise_for_status()
output = Path('cosmos3_edge_i2v.mp4')
output.write_bytes(response.content)
print(f'Saved {output} ({len(response.content):,} bytes)')
PY
ffprobe -v error -select_streams v:0 -show_entries stream=width,height,nb_frames,r_frame_rate -of default=noprint_wrappers=1 cosmos3_edge_i2v.mp4