JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2026-05-13 03:25:35 +08:00
Code Issues Packages Projects Releases Wiki Activity
458 Commits 3 Branches 1 Tag
Commit Graph

458 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
IMaloney
94a5656836
Merge 206760830a9c56a789a2ec59237bb655411751ce into 7a1af7154511e0ce4e4be8d62faa8c5e5a3532d2 2026-02-18 22:42:05 -05:00
Test User
206760830a chore: allow tests/ directory in gitignore 2026-02-19 03:36:33 +00:00
Test User
15a4b403c4 test: add comprehensive tests for batch inference pipeline 2026-02-19 03:24:16 +00:00
Test User
2d3f2a4d02 feat: add production-grade batch inference pipeline 
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
 2026-02-19 03:15:10 +00:00
tengjiayan
7a1af71545 update readme 2025-11-04 19:15:43 +08:00
zRzRzRzRzRzRzR
a3429723be update readme 2025-11-04 18:10:07 +08:00
Yuxuan Zhang
0e179ee52c
Merge pull request #788 from yuting89830/patch-1 
Update README_zh.md
 2025-09-07 20:50:45 +08:00
311555007
7303927cf7
Update README_zh.md 2025-07-23 22:12:39 +08:00
Yuxuan Zhang
aaab2877ec
Merge pull request #774 from emmanuel-ferdman/main 
Resolve Python Logger warnings
 2025-06-17 10:08:33 +08:00
Emmanuel Ferdman
39a007a41f
Resolve Python Logger warnings 
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
 2025-05-14 06:23:56 -07:00
OleehyO
e519eced78
Update README_zh.md 2025-05-14 11:07:02 +08:00
OleehyO
657eee4379
Update README_zh.md 2025-05-14 11:05:17 +08:00
OleehyO
503a9faa93
Update README.md 2025-05-14 11:03:41 +08:00
OleehyO
5ab1e2449f
Merge pull request #719 from holma91/fix-lora-scale 
fix scale bug
 2025-03-25 18:59:49 +08:00
OleehyO
a01ffd9aba
Update cli_demo.py 2025-03-25 18:59:11 +08:00
OleehyO
9be282d461
Merge branch 'main' into fix-lora-scale 2025-03-25 18:58:33 +08:00
Yuxuan Zhang
c624cb0d91
Merge pull request #743 from THUDM/CogVideoX_dev 
Format
 2025-03-24 11:30:17 +08:00
Yuxuan Zhang
39c6562dc8 format 2025-03-22 15:14:06 +08:00
Yuxuan Zhang
b9b0539dbe update 2025-03-15 14:27:12 +08:00
Yuxuan Zhang
129c375c85
Merge pull request #729 from zhuhz22/riflex 
Add friendly link of RIFLEx
 2025-03-03 10:57:29 +08:00
Yuxuan Zhang
536b705105
Merge pull request #730 from THUDM/CogVideoX_dev 
Update wechat.jpg
 2025-03-03 10:56:19 +08:00
Yuxuan Zhang
a691a6dd35 Update wechat.jpg 2025-03-03 10:52:22 +08:00
zhuhz22
6454293a1d add friendly link of RIFLEx 2025-03-01 22:06:39 +08:00
Yuxuan Zhang
887a4c7365
Merge pull request #726 from THUDM/CogVideoX_dev 
Readme of ddim inverse
 2025-03-01 09:29:09 +08:00
Yuxuan Zhang
a494fa50cd Merge branch 'CogVideoX_dev' of https://github.com/THUDM/CogVideo into CogVideoX_dev 2025-02-27 17:33:23 +08:00
Yuxuan Zhang
4fb6766d7c fix import decord error 2025-02-27 17:33:20 +08:00
Yuxuan Zhang
8d90381ba8
Merge pull request #722 from THUDM/main 
merge
 2025-02-27 17:32:24 +08:00
Yuxuan Zhang
eb66c9c6dc
Merge pull request #709 from LittleNyima/feature/ddim-inversion 
Implement DDIM Inversion for CogVideoX
 2025-02-27 13:24:24 +08:00
LittleNyima
2c33c0982b fix import order and deprecate for CVX 2B models 2025-02-26 15:54:58 +08:00
LittleNyima
d6bb910697
Merge branch 'THUDM:main' into feature/ddim-inversion 2025-02-26 15:22:08 +08:00
holma91
84766d02e8 fix scale bug 2025-02-24 20:08:27 +01:00
LittleNyima
e0bf395458
make the style of argparser consistent with repo 2025-02-23 19:41:21 +08:00
Yuxuan Zhang
e44c9f2c83
Merge pull request #716 from THUDM/CogVideoX_dev 
Update gitignore patterns and project dependencies
 2025-02-22 17:09:50 +08:00
OleehyO
5be6c0512f Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev 2025-02-22 06:06:03 +00:00
OleehyO
4dac252c63 [chore] Update gitignore patterns and project dependencies 2025-02-22 06:03:53 +00:00
LittleNyima
250a0bce45 stable version 2025-02-20 05:03:15 +00:00
LittleNyima
58d66c8a08
Implement an unverified version that should be further tested 2025-02-20 01:39:12 +08:00
LittleNyima
dd76b2b9ea Initialize DDIM Inversion script 2025-02-18 09:50:55 +00:00
Yuxuan Zhang
34c6ba22ab
Merge pull request #682 from THUDM/main 
Synchronize two branches.
 2025-01-22 09:49:34 +08:00
Yuxuan Zhang
bbe909d7f7
Merge pull request #678 from THUDM/CogVideoX_dev 
docs: clarify frame number requirements for CogVideoX models
 2025-01-22 09:47:24 +08:00
Yuxuan Zhang
ea994c75c2
Merge pull request #652 from erfanasgari21/moviepy-v2 
Update code and requirements to support Moviepy v2
 2025-01-21 22:29:15 +08:00
Yuxuan Zhang
aa12ed37f5
Merge branch 'main' into moviepy-v2 2025-01-20 21:46:07 +08:00
OleehyO
d9e2a415e8 fix: fix resolution handling for different model types 2025-01-20 09:48:17 +00:00
OleehyO
0e26f54cbe docs: clarify frame number requirements for CogVideoX models 
Specify that frame numbers must be:
- 16N + 1 (N <= 10) for CogVideoX1.5-5B models
- 8N + 1 (N <= 6) for CogVideoX-2B/5B models
 2025-01-20 09:43:45 +00:00
Yuxuan Zhang
c1ca70ba67
Merge pull request #654 from THUDM/CogVideoX_dev 
Support SFT using ZeRO
 2025-01-20 11:15:50 +08:00
OleehyO
bf73742c05 docs: enhance CLI demo documentation 2025-01-16 09:34:52 +00:00
OleehyO
bf9c351a10 deps: upgrade diffusers to >=0.32.1 2025-01-16 09:08:44 +00:00
OleehyO
0e78f20629 Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev 2025-01-14 04:00:11 +00:00
Yuxuan Zhang
4615479b51 move to tools 2025-01-14 11:33:02 +08:00
Yuxuan Zhang
7993670957 zero_to_bf16 2025-01-14 11:31:25 +08:00