PaddlePaddle/PaddleMIX

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

64
/ 100
Established

Built on PaddlePaddle, it provides unified training pipelines across vision-language understanding (LLaVA, Qwen-VL, DeepSeek-VL2), text-to-image generation (Stable Diffusion, FLUX), and video generation with specialized models like PP-DocBee for document understanding and PP-VCtrl for video control. The toolkit includes Fast-Diffusers acceleration algorithms (training-free inference optimization and distillation techniques achieving 2x+ speedup), multi-modal data processing via DataCopilot, and distributed training support across GPU and Ascend 910B chips via PaddlePaddle's 4D hybrid parallelism.

718 stars. Actively maintained with 1 commit in the last 30 days.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

718

Forks

224

Language

Python

License

Apache-2.0

Last pushed

Mar 06, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PaddlePaddle/PaddleMIX"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.