ppdiffusers

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.

https://github.com/paddlepaddle/paddlemix

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Committers with academic emails
    3 of 87 committers (3.4%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.4%) to scientific vocabulary

Keywords

aigc clip controlnet deepseek-vl dit eva-clip got-ocr20 image-to-text internvl2 llava minicpm-v multimodal ppdiffusers qwen2-vl sd-xl sora stable-diffusion stablevideodiffusion text-to-image text-to-video

Keywords from Contributors

ai4science operator-learning paddlepaddle self-supervised-learning supervised-learning actbert action-detection action-localization action-recognition activitynet
Last synced: 6 months ago · JSON representation

Repository

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.

Basic Info
  • Host: GitHub
  • Owner: PaddlePaddle
  • License: apache-2.0
  • Language: Python
  • Default Branch: develop
  • Homepage:
  • Size: 188 MB
Statistics
  • Stars: 696
  • Watchers: 24
  • Forks: 218
  • Open Issues: 151
  • Releases: 3
Topics
aigc clip controlnet deepseek-vl dit eva-clip got-ocr20 image-to-text internvl2 llava minicpm-v multimodal ppdiffusers qwen2-vl sd-xl sora stable-diffusion stablevideodiffusion text-to-image text-to-video
Created over 2 years ago · Last pushed 6 months ago
Metadata Files
Readme License Citation

README.md

2025.04.21FLUX

  • PaddleMIXFLUXPaddleMIXFLUX421https://www.wjx.top/vm/QTuwoyG.aspx?udsid=997416

2025.07.14 Fast-Diffusers * Training-FreeT-gatePABTeaCacheTaylorSeerBlockDanceSOTA Training-FreeSortBlockTeaBlockCache, CG-TaylorFirstBlockTaylor2 * PCMDMD2lossFLUX-dev41.66

2025.05.09 PaddleMIX v3.0-beta * Qwen2.5VLDeepSeek-VL2PP-DocBeeQwen2.5VLvllm 11.5% * PPDiffusers 0.29.1PP-VCtrlSD3 ControlNetSD3.5

** 2025.01.08 PP-VCtrl** * PP-VCtrl

** 2025.01.02 PP-DocBee** * PP-DocBeePP-DocBeeSOTA

** 2024.10.31 [](paddlemix_applications.md)** * 96,30,25 * - [AI Studio](https://aistudio.baidu.com/aistudio/community/multimodal?from=singlemessage) **2024.10.11 PaddleMIX v2.1** * [PaddleNLP 3.0 beta](https://github.com/PaddlePaddle/PaddleNLP/releases/tag/v3.0.0-beta0) * [Qwen2-VL](./paddlemix/examples/qwen2_vl/)[InternVL2](./paddlemix/examples/internvl2/)[Stable Diffusion 3 (SD3)](https://github.com/PaddlePaddle/PaddleMIX/blob/develop/ppdiffusers/examples/dreambooth/README_sd3.md) * [PP-InsCapTagger](./paddlemix/datacopilot/example/pp_inscaptagger/)50% * InternVL2LLaVASD3SDXL910B **2024.07.25 PaddleMIX v2.0** * LLaVAQwen-VLAutoSFTmixtokenSFT5.6 * [PPDiffusers 0.24.1](./ppdiffusers/README.md)LCMpeftaccelerateComfyUI * [DataCopilot](./paddlemix/datacopilot/) **2023.10.7 PaddleMIX v1.0** * BLIP-2 * [AppFlow](./applications/README.md)11 * [PPDiffusers](./ppdiffusers/README.md) 0.19.3 SDXL

PaddleMIX

| ComfyUI | R1+MIX | **** | | :--------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------: | | | | | | **** | AI50+Lora | **** | | | | |

PaddleMIX


PaddleMIX``

PaddleMIX ``

PaddleMIX4D``benchmark

PaddleMIXPP-DocBeePP-VCtrlDataCopilot``

1. PaddleMIX

git clone https://github.com/PaddlePaddle/PaddleMIX cd PaddleMIX

2.

conda create -n paddlemix python=3.10 -y conda activate paddlemix

3. PaddlePaddle

1: GPU/CPU

  • CUDA 11.x12.x
  • PaddlePaddle 3.1.0 sh build_paddle_env.sh

2:

PaddlePaddleInstallation

4.

1:

: sh build_env.sh

2:

```bash

PaddleMIX

pip install -e .

ppdiffusers

cd ppdiffusers pip install -e . cd .. ```

5.

```bash sh check_env.sh

: - paddlepaddle: 3.1.0develop - paddlenlp: 3.0.0b4 - ppdiffusers: 0.30.0 - huggingface_hub: 0.23.0 ```




-

- LLaVA

benchmark - benchmark - benchmark



  • 910B
  • P800
  • |

    PP-DocBee

    PaddleMIXPP-DocBeeSOTA

    PP-VCtrl

    PaddleMIXPP-VCtrl

    DataCopilot

    PaddleMIXDataCopilotPaddleMIX``DataCopilot

    PP-InsCapTagger(Instance Capability Tagger) DataCopilot PaddleMIX LLaVA SFTLLaVASFT50%

    PP-InsCapTagger() | Model | ScienceQA | TextVQA | VQAv2 | GQA | MMMU | MME | |----------------------------------|-----------------------------------------|----------------------------------------|----------------------------------------|----------------------------------------|----------------------------------------|-----------------------------------------| | llava-1.5-7b (origin) | 66.8 | 58.2 | 78.5 | 62 | - | - | | llava-1.5-7b (rerun) | 69.01 | 57.6 | 79 | 62.95 | 36.89 | 1521
    323 | | llava-1.5-7b (random 50%) | 67.31 | 55.6 | 76.89 | 61.01 | 34.67 | 1421
    286 | | **llava-1.5-7b (our 50%)** | **70.24** *(+2.93)* | **57.12** *(+1.52)* | **78.32** *(+1.43)* | **62.14** *(+1.13)* | **37.11** *(+2.44)* | **1476** *(+55)*
    **338** *(+52)* | ``[pp_inscaptagger](paddlemix/datacopilot/example/pp_inscaptagger/readme.md)

    FAQ

    FAQIssues

    Apache 2.0 license

    @misc{paddlemix2023, title={PaddleMIX, Paddle Multimodal Integration and eXploration.}, author={PaddlePaddle Authors}, howpublished = {\url{https://github.com/PaddlePaddle/PaddleMIX}}, year={2023} }

    Owner

    • Name: PaddlePaddle
    • Login: PaddlePaddle
    • Kind: organization

    Committers

    Last synced: 9 months ago

    All Time
    • Total Commits: 966
    • Total Committers: 87
    • Avg Commits per committer: 11.103
    • Development Distribution Score (DDS): 0.875
    Past Year
    • Commits: 509
    • Committers: 58
    • Avg Commits per committer: 8.776
    • Development Distribution Score (DDS): 0.864
    Top Committers
    Name Email Commits
    LokeZhou a****q@1****m 121
    luyao-cv 1****8@q****m 106
    nifeng n****s@q****m 81
    xuzhang w****h@1****m 66
    wjm202 8****4@q****m 58
    changwenbin c****n@b****m 50
    yujun 5****7@q****m 44
    lyuwenyu w****u@g****m 37
    wangguanzhong j****z@1****m 35
    kui huang 8****1 33
    cheng221 9****1 30
    co63oc c****c 28
    Shixian Sheng s****2@f****u 18
    来新璐 3****M 16
    Milen 1****0@q****m 15
    zhuyipin y****u@o****m 15
    zhiboniu z****u@1****m 14
    coco 6****e 12
    sneaxiy 3****y 11
    yangrongxinuser 1****r 10
    Hammingbo 1****2@q****m 8
    Birdylx 2****x 8
    LielinJiang 5****g 8
    周周周 3****6 8
    张春乔 8****e 8
    liuyuang l****g@b****m 7
    swagger-coder 1****5@q****m 7
    Tsaiyue 4****e 6
    LixinGuo 1****4@1****m 6
    Jiaxing Yan 4****t 6
    and 57 more...
    Committer Domains (Top 20 + Academic)

    Issues and Pull Requests

    Last synced: 6 months ago

    All Time
    • Total issues: 144
    • Total pull requests: 1,378
    • Average time to close issues: about 1 month
    • Average time to close pull requests: 6 days
    • Total issue authors: 94
    • Total pull request authors: 106
    • Average comments per issue: 1.49
    • Average comments per pull request: 1.06
    • Merged pull requests: 1,012
    • Bot issues: 0
    • Bot pull requests: 0
    Past Year
    • Issues: 75
    • Pull requests: 1,022
    • Average time to close issues: 13 days
    • Average time to close pull requests: 4 days
    • Issue authors: 54
    • Pull request authors: 70
    • Average comments per issue: 1.68
    • Average comments per pull request: 1.1
    • Merged pull requests: 772
    • Bot issues: 0
    • Bot pull requests: 0
    Top Authors
    Issue Authors
    • luyao-cv (9)
    • westfish (6)
    • yimuu (5)
    • whisky-12 (4)
    • co63oc (4)
    • dddlli (3)
    • chenjjcccc (3)
    • shiyutang (3)
    • lrjxgl (3)
    • Tortoise17 (3)
    • ZhijunLStudio (3)
    • lyuwenyu (3)
    • JunnYu (2)
    • knoka812 (2)
    • fxy1699 (2)
    Pull Request Authors
    • luyao-cv (155)
    • nemonameless (120)
    • LokeZhou (98)
    • cheng221 (78)
    • pkhk-1 (75)
    • chang-wenbin (65)
    • westfish (61)
    • lyuwenyu (57)
    • warrentdrew (47)
    • jerrywgz (46)
    • co63oc (45)
    • swagger-coder (38)
    • CrazyBoyM (35)
    • LielinJiang (22)
    • Hammingbo (20)
    Top Labels
    Issue Labels
    HappyOpenSource Pro (9) HappyOpenSource (5) contributor (4) PaddlePaddle Hackathon (1)
    Pull Request Labels
    contributor (252) HappyOpenSource (68) HappyOpenSource Pro (19) PaddlePaddle Hackathon (10) XPU (3)

    Packages

    • Total packages: 1
    • Total downloads:
      • pypi 3,264 last-month
    • Total docker downloads: 27
    • Total dependent packages: 1
    • Total dependent repositories: 65
    • Total versions: 19
    • Total maintainers: 1
    pypi.org: ppdiffusers

    PPDiffusers: Diffusers toolbox implemented based on PaddlePaddle

    • Versions: 19
    • Dependent Packages: 1
    • Dependent Repositories: 65
    • Downloads: 3,264 Last month
    • Docker Downloads: 27
    Rankings
    Dependent repos count: 1.8%
    Dependent packages count: 3.3%
    Docker downloads count: 3.6%
    Downloads: 3.7%
    Average: 4.5%
    Stargazers count: 7.2%
    Forks count: 7.3%
    Maintainers (1)
    Last synced: 6 months ago