mirror of
https://github.com/THUDM/CogVideo.git
synced 2026-05-06 22:58:13 +08:00
2d3f2a4d02
Implements a comprehensive batch video generation tool that addresses the #1 missing feature for production users: generating multiple videos from a single batch file instead of one-at-a-time processing. ## New Files ### tools/batch_inference.py Production-ready batch inference script with: **Core Features:** - JSONL input format (one job per line, streaming-friendly) - Support for all generation types: t2v, i2v, v2v - Progress tracking with tqdm (progress bar, ETA) - Robust error handling (logs errors, continues batch) - Resume capability (tracks completed jobs, skips on restart) **Input Schema:** - prompt (required): Text description - output_name (required): Output filename - image_path (optional): For i2v generation - video_path (optional): For v2v generation - num_frames, guidance_scale, num_inference_steps, seed, width, height (optional) **Multi-GPU Support:** - Job-level parallelism via --gpu_id and --num_gpus flags - Each GPU processes a subset of jobs (round-robin distribution) - State file prevents duplicate work across processes **Memory Management:** - Loads model once, generates sequentially - CPU offloading enabled by default - VAE slicing and tiling enabled ### resources/example_batch_*.jsonl Example batch files demonstrating: - example_batch_t2v.jsonl: Text-to-video prompts - example_batch_i2v.jsonl: Image-to-video with image_path - example_batch_v2v.jsonl: Video-to-video with video_path ## Design Decisions 1. **JSONL over JSON**: Better for large batches, streaming, and manual editing 2. **Reuse generation logic**: Mirrors cli_demo.py patterns for consistency 3. **Single model per batch**: Memory efficient, simpler implementation 4. **State persistence**: JSON state file enables reliable resume 5. **Error isolation**: One failed job doesn't stop the batch ## Usage Examples # Basic text-to-video python tools/batch_inference.py --batch_file prompts.jsonl --model_path THUDM/CogVideoX1.5-5B # Multi-GPU (4 GPUs) for i in {0..3}; do CUDA_VISIBLE_DEVICES=$i python tools/batch_inference.py --batch_file batch.jsonl --gpu_id $i --num_gpus 4 & done
13 lines
1.3 KiB
JSON
13 lines
1.3 KiB
JSON
# Example text-to-video batch file
|
|
# Each line is a JSON object with prompt and output_name (required)
|
|
# Optional: num_frames, guidance_scale, num_inference_steps, seed, width, height
|
|
|
|
{"prompt": "A majestic eagle soaring through golden sunset clouds, cinematic lighting, 4K quality", "output_name": "eagle_sunset.mp4"}
|
|
{"prompt": "A cozy coffee shop on a rainy day, steam rising from cups, warm ambient lighting", "output_name": "coffee_shop_rain.mp4", "num_frames": 49}
|
|
{"prompt": "An astronaut floating in space with Earth visible in the background, peaceful and serene", "output_name": "astronaut_space.mp4", "seed": 123}
|
|
{"prompt": "A field of sunflowers swaying gently in the summer breeze, bright and cheerful", "output_name": "sunflowers.mp4", "guidance_scale": 7.0}
|
|
{"prompt": "A futuristic city at night with neon lights and flying cars, cyberpunk aesthetic", "output_name": "cyberpunk_city.mp4", "num_inference_steps": 60}
|
|
{"prompt": "A serene Japanese garden with cherry blossoms falling, koi pond, peaceful atmosphere", "output_name": "japanese_garden.mp4"}
|
|
{"prompt": "Waves crashing on a tropical beach at sunset, palm trees silhouetted against orange sky", "output_name": "tropical_sunset.mp4"}
|
|
{"prompt": "A mystical forest with glowing mushrooms and fireflies, fantasy atmosphere", "output_name": "mystical_forest.mp4", "seed": 456}
|