Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
replicate-mcp-server
MCP serversReplicate MCP server - image, video, audio, speech, LLM, vision, upscale, 3D, training. 36 tools.
replicate-mcp-server@3.3.1 -
LFM3-Omni-2B-GGUF
Modelsany to any model by LiquidAI · gguf
LiquidAI/LFM3-Omni-2B-GGUF -
MiniMax-M3.1-Flash-GGUF
Modelsimage text to text model by unsloth
unsloth/MiniMax-M3.1-Flash-GGUF -
OpenAI: GPT-4 Turbo (batch)
ModelsThe latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
openai/gpt-4-turbo:batch -
suno
Datasets & benchmarksHugging Face dataset by nyuuzyou
nyuuzyou/suno -
aurora
Datasets & benchmarks[ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
git clone https://github.com/wenhaochai/aurora.git -
Callirra
MCP serversCreate images, video and audio; chat with multimodal AI; manage assets and reusable workflows.
@callirra/mcp@0.3.1 -
Mixpeek
MCP serversGive your agent eyes. Search video, images, and audio via the Mixpeek multimodal retrieval API.
@mixpeek/mcp@0.1.1 -
video-search-and-summarization
AI repositoriesNVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git -
meta-encoder-v1
Modelsfeature extraction model by facebook · transformers
facebook/meta-encoder-v1 -
awesome-agent-apis
AI repositories660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsable by capability.
git clone https://github.com/Anil-matcha/awesome-agent-apis.git -
d3
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3 -
Mistral: Ministral 3 8B 2512
ModelsA balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
mistralai/ministral-8b-2512 -
Mistral: Ministral 3 3B 2512
ModelsThe smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
mistralai/ministral-3b-2512 -
Google: Gemma 3 4B
ModelsGemma 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,...
google/gemma-3-4b-it -
Google: Gemma 3 12B
ModelsGemma 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,...
google/gemma-3-12b-it -
Google: Gemma 3 27B
ModelsGemma 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,...
google/gemma-3-27b-it -
WeVisCut
Modelsany to any model by tencent · transformers
tencent/WeVisCut -
cerul
Agents & frameworksOpen-source video processing core and CLI. Search and annotate local videos with your own model endpoints.
git clone https://github.com/cerul-ai/cerul.git -
d3-flash
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-flash -
d3-turbo
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-turbo -
LivePortrait
Tools & appsHugging Face space by KlingTeam
KlingTeam/LivePortrait -
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
thinkingmachines/inkling-small -
VideoGLaMM
Agents & frameworks[CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
git clone https://github.com/mbzuai-oryx/VideoGLaMM.git
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.