Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Sport Vision
Public APIsIdentify sport, brands and gear in an image. Also does image sports captioning
-
Qwen2.5-VL-7B-Instruct
Modelsimage text to text model by Qwen · transformers
Qwen/Qwen2.5-VL-7B-Instruct -
Qwen2-VL-7B-Instruct
Modelsimage text to text model by Qwen · transformers
Qwen/Qwen2-VL-7B-Instruct -
llava-v1.5-13b
Modelsimage text to text model by liuhaotian · transformers
liuhaotian/llava-v1.5-13b -
clef
Modelsimage text to text model by Cloudflare · transformers
Cloudflare/clef -
MiniCPM-V-4.6
Modelsimage text to text model by openbmb · transformers
openbmb/MiniCPM-V-4.6 -
moondream3-preview
Modelsimage text to text model by moondream · transformers
moondream/moondream3-preview -
RolmOCR
Modelsimage text to text model by reducto · transformers
reducto/RolmOCR -
Kimi-K3.1-Pro
Modelsimage text to text model by moonshotai · transformers
moonshotai/Kimi-K3.1-Pro -
Muse-Glimmer-30B-GGUF
Modelsimage text to text model by meta-models
meta-models/Muse-Glimmer-30B-GGUF -
llava-v1.6-34b
Modelsimage text to text model by liuhaotian · LLaVA
liuhaotian/llava-v1.6-34b -
Nanonets-OCR-s
Modelsimage text to text model by nanonets · transformers
nanonets/Nanonets-OCR-s -
gemma-3-12b-it
Modelsimage text to text model by google · transformers
google/gemma-3-12b-it -
gemma-4-31B-it-GGUF
Modelsimage text to text model by unsloth
unsloth/gemma-4-31B-it-GGUF -
Kimi-K3-GGUF
Modelsimage text to text model by unsloth · transformers
unsloth/Kimi-K3-GGUF -
vision-squeezer
MCP serversShrink images to a token budget for vision LLM agents and pipelines. Not for chat-pasted images.
vision-squeezer@0.9.0 -
PaddleOCR-VL
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL -
gemma-4-E4B-it
Modelsany to any model by google · transformers
google/gemma-4-E4B-it -
dsh-media-skills
SkillsFree image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2 / v0.1.2-alpha.3) — paste-image reading with auto vision transcription, DeepSeek-V4-Flash-Vision-Exp / GLM-4V-Flash / SenseNova / Gemini failover, Kolors + U1 Fast generation. No keys in repo.
git clone https://github.com/MJorgin/dsh-media-skills.git -
pixtral-12b-240910
Modelsimage text to text model by mistral-community · vllm
mistral-community/pixtral-12b-240910 -
SmolVLM-256M-Instruct
Modelsimage text to text model by HuggingFaceTB · transformers
HuggingFaceTB/SmolVLM-256M-Instruct -
deepseek-vl2
Modelsimage text to text model by deepseek-ai · transformers
deepseek-ai/deepseek-vl2 -
Fara-7B
Modelsimage text to text model by microsoft · transformers
microsoft/Fara-7B -
image text to text model by Jackrong
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
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.