open-weights 开源项目推荐（213 个）

D3voz /openjutsu

One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative built on ComfyUI and MiniMax H3, with FLUX.3 Klein relighting.

StartLuxLabs /StartLux-Decision

类型化决策模型从0.8B到27B。每个问题都会返回每个选项的概率。

sahibzada-allahyar /gliner2-ultrafast

Real browser automation with local GLiNER2 inference and open weights. Work in progress. Contributions welcome.

ikermoel /open-alternative-jev

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

lucataco /open-source-higgsfield

Same take, new cast: open-weights video character recasting on local ComfyUI with SAM 3.1, FLUX 3 Image Klein and SCAIL-2. Built for #OpenSourceHiggsfield.

thePloggy /CreatorOS-Studio

Open-source Higgsfield on your own GPU: train a recurring character, turn a one-line brief into an edited reel, move the camera, re-shoot an angle, block shots in 3D, sketch to video, restore old footage. Runs on local ComfyUI, open-weights models only.

lukeckprobierts /Hemmingway-1

Hemmingway-1: a 27B model that writes the way a person writes. Open weights, free for non-commercial use (CC BY-NC 4.0); commercial use by agreement.

hopit-ai /Moda

MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hosted). Full-corpus benchmarks vs FashionSigLIP, SigLIP-SO400M and ZooClaw — one harness, losses shown. #1 open model on LookBench.

workingprototype /Fuobe

The open creative studio on ComfyUI: images, video, 3D and audio on open weights, on your own GPU or the cloud. Camera motions, effects, apps, Cinema, Layers, Image to 3D and an AI agent.

chenthedesignmaker /ComfyUI-Picky

Render it ten ways, keep the one you love. An open-weights film studio for MiniMax H3 in ComfyUI: takes, lineage, cast and an agent skill.

EvoLinkAI /awesome-ideogram-4.0-prompts

Curated Ideogram 4.0 prompts and image examples — typography, photorealistic portraits, product/UI mockups, and model comparisons. By Evolink.

Anil-matcha /awesome-uncensored-ai-video-models

A community-maintained catalog of open, low-filter, and community-reported AI video models, checkpoints, adapters, and endpoints.

cobusgreyling /Muse-Glimmer

Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apache 2.0 · on-device AI · function calling

Burgstall-labs /ComfyUI-SpEdE

SpEdE, the Splat Edit Engine: click an object in a Gaussian splat, then Remove, Replace or Extract it. Local ComfyUI nodes + web Studio, open weights only. #OpenSourceHiggsfield

Singularity-Compute /super-decider

Decisions, not essays: a choice, a yes or no, or a score with a calibrated probability. Open weights, Jev-compatible API, adaptive thinking.

bahree /ModelAdaptationBook

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.

bagusardin25 /WicaraLLM

WicaraLLM is our Indonesian Small Language Model (56M parameters), built from scratch and trained on a 1.3B-token Indonesian corpus. Engineered to run efficiently on a single laptop GPU with just 6 GB of VRAM, it combines GQA, RoPE, SwiGLU, and RMSNorm, with supervised fine-tuning for conversational capabilities

Trac-Systems /openmayhem

OpenMayhem is an open-source and decentralized inference router for consumer & pro hardware. Providers earn, users/agents access cheap inference.

Eximius-Labs /fusion-embedding

One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.

Anil-matcha /awesome-uncensored-ai-image-models

A community-maintained catalog of open and low-filter AI image models, checkpoints, and local inference resources.