InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

3,785 results Clear search and filters
  1. ChartVerse-SFT-1.8M

    Datasets & benchmarks

    Hugging Face dataset by opendatalab

    Stale Hugging Face Hub, opendatalab 140 ♥apache-2.0Updated 9 months ago

    opendatalab/ChartVerse-SFT-1.8M
  2. 为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

    Stale GitHub, Anionex 1,232 ★MITUpdated 34 days ago

    git clone https://github.com/Anionex/agent-vision-toolkit.git
  3. image text to text model by saidutta69 · transformers

    Stale Hugging Face Hub, saidutta69 25 ♥apache-2.0Updated 10 days ago

    saidutta69/Qwen3.5-4B-heretic
  4. image text to text model by Jackrong · transformers

    Stale Hugging Face Hub, Jackrong 24 ♥apache-2.0Updated 34 days ago

    Jackrong/Qwopus3-5-9B-Coder-Flash-GGUF
  5. DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

    Indexed OpenRouter model list, deepseek Updated 2 months ago

    deepseek/deepseek-v4-flash-vision-exp
  6. dsh-iris

    Skills

    Media generation and visual understanding for DeepSeek Harness, with multi-provider routing and the integrated Iris workbench.

    Indexed GitHub, mokuyoaxis 11 ★MITUpdated today

    git clone https://github.com/mokuyoaxis/dsh-iris.git
  7. model by lightx2v · minimax-h3

    Stale Hugging Face Hub, lightx2v 92 ♥Updated 18 days ago

    lightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA
  8. image text to text model by nerkyor · ninfer

    Stale Hugging Face Hub, nerkyor 52 ♥apache-2.0Updated 29 days ago

    nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer
  9. VisualNews-Repository

    Datasets & benchmarks

    [EMNLP'21] Visual News: Benchmark and Challenges in News Image Captioning

    Stale GitHub, FuxiaoLiu 106 ★Updated 2 years ago

    git clone https://github.com/FuxiaoLiu/VisualNews-Repository.git
  10. mmagic

    AI repositories

    OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

    Stale GitHub, open-mmlab 7,474 ★Apache-2.0Updated 2 years ago

    git clone https://github.com/open-mmlab/mmagic.git
  11. The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

    Indexed OpenRouter model list, openai Updated 2 years ago

    openai/gpt-4-turbo:batch
  12. Janus

    AI repositories

    Janus-Series: Unified Multimodal Understanding and Generation Models

    Stale GitHub, deepseek-ai 17.8k ★MITUpdated 21 months ago

    git clone https://github.com/deepseek-ai/Janus.git
  13. Reka Edge

    Models

    Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

    Indexed OpenRouter model list, rekaai Updated 8 months ago

    rekaai/reka-edge
  14. Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

    Indexed OpenRouter model list, qwen Updated 13 months ago

    qwen/qwen3-vl-8b-instruct
  15. A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/ministral-8b-2512
  16. The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/ministral-3b-2512
  17. claude-video-vision

    MCP servers

    Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

    Stale GitHub, jordanrendric 1,366 ★MITUpdated 33 days ago

    git clone https://github.com/jordanrendric/claude-video-vision.git
  18. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

    Indexed OpenRouter model list, google Updated 20 months ago

    google/gemma-3-4b-it
  19. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

    Indexed OpenRouter model list, google Updated 20 months ago

    google/gemma-3-12b-it
  20. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

    Indexed OpenRouter model list, google Updated 20 months ago

    google/gemma-3-27b-it
  21. Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

    Indexed OpenRouter model list, qwen Updated 13 months ago

    qwen/qwen3-vl-235b-a22b-instruct
  22. Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

    Indexed OpenRouter model list, stepfun Updated 5 months ago

    stepfun/step-3.7-flash
  23. SimpleMem

    AI repositories

    [ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

    Stale GitHub, aiming-lab 3,832 ★MITUpdated 3 months ago

    git clone https://github.com/aiming-lab/SimpleMem.git
  24. Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.7-flash

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.