Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Curated Gemini Omni prompts, API guide, and video examples — video generation, editing, camera control, style transfer, text rendering, and multi-modal workflows.
git clone https://github.com/Evolink-AI/awesome-gemini-omni-1.2-flash-API-guide-and-prompt.git -
LLM-TPU
AI repositoriesRun generative AI models in sophgo BM1684X/BM1688
git clone https://github.com/sophgo/LLM-TPU.git -
Qwen: Qwen2.5 7B Instruct
ModelsQwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
qwen/qwen-2.5-7b-instruct -
d1-omni-600M
Modelsimage text to text model by LiquidAI · transformers
LiquidAI/d1-omni-600M -
Omni-SafetyBench
Datasets & benchmarks[ACM MM 2026 Oral] Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".
git clone https://github.com/THU-BPM/Omni-SafetyBench.git -
text to image model by chatrlabs · diffusers
chatrlabs/Qwen-Image-2.1-Uncensored-Omni-Quantized -
model by FastVideo · diffusers
FastVideo/FastVideo-FastH3-Omni-8-Step-V1 -
d1-Omni-2B
Modelsaudio text to text model by LiquidAI · transformers
LiquidAI/d1-Omni-2B -
Omni-MATH
Datasets & benchmarksHugging Face dataset by KbsdJames
KbsdJames/Omni-MATH -
Qwen2.5 Coder 32B Instruct
ModelsQwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...
qwen/qwen-2.5-coder-32b-instruct -
MiniMax-Music3
Modelstext to audio model by MiniMaxAI · diffusers
MiniMaxAI/MiniMax-Music3 -
OmniScience
Datasets & benchmarksHugging Face dataset by UniParser
UniParser/OmniScience -
ms-swift
AI repositoriesUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
git clone https://github.com/modelscope/ms-swift.git -
LoCo-7B
Modelstext generation model by MuyaoYuan · transformers
MuyaoYuan/LoCo-7B -
OmniEdit-Filtered-1.2M
Datasets & benchmarksHugging Face dataset by TIGER-Lab
TIGER-Lab/OmniEdit-Filtered-1.2M -
OmniChar
AI repositoriesThe open .char format for consistent characters. Face, body, wardrobe & voice in one file, consistent across every model.
git clone https://github.com/omnichar/OmniChar.git -
FocusRelayMCP
MCP serversFast native Swift OmniFocus MCP server and CLI for macOS. Let AI assistants safely read, update, complete, and organize tasks and projects through documented Omni Automation APIs.
git clone https://github.com/deverman/FocusRelayMCP.git -
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
qwen/qwen2.5-vl-72b-instruct -
text to image model by chatrlabs · diffusers
chatrlabs/Qwen-Image-2.1-Uncensored-Omni-LoRA-v0.1 -
s2-pro
Modelstext to speech model by fishaudio
fishaudio/s2-pro -
omnilingual-asr-corpus
Datasets & benchmarksHugging Face dataset by facebook
facebook/omnilingual-asr-corpus -
bytedesk
AI repositoriesOpen Souce IM with AI powered live-chat, email, ticket support, omni-channel customer service,alternative to slack + zendesk
git clone https://github.com/Bytedesk/bytedesk.git -
Chatway: Omnichannel Customer Support
MCP serversShared inbox for website live chat, WhatsApp Business, Facebook Messenger, Instagram DMs & email.
-
mcp-omnisearch
MCP servers🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.
git clone https://github.com/spences10/mcp-omnisearch.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.