open-weights repositories

Trending repositories tagged open-weights, ranked by trending score. Updated daily.

  1. 1
    neuregex/freefield

    Open-source Higgsfield on ComfyUI: 120 image, video, VFX and audio apps, every model open weights; runs on Modal or your own GPU

    GitHub · Python · 1,669 stars · 319 forks · +64 stars in 24 hours · Trending score 3.83

  2. 2
    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.

    GitHub · TypeScript · 2,531 stars · 397 forks · +35 stars in 24 hours · Trending score 3.27

  3. 3
    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

    GitHub · Python · 42 stars · 7 forks · +22 stars in 24 hours · Trending score 2.35

  4. 4
    StartLuxLabs/StartLux-Decision

    Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

    GitHub · Python · 1,781 stars · 170 forks · +7 stars in 24 hours · Trending score 1.87

  5. 5
    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.

    GitHub · Python · 19 stars · 0 forks · +10 stars in 24 hours · Trending score 1.64

  6. 6
    jutsuhq/open-source-higgsfield

    Open-source Higgsfield AI alternatives on GitHub: 117 projects, 110 of them from ComfyUI's #OpenSourceHiggsfield challenge, with its 16 prize winners. Character swap (OPENjutsu), effects, camera re-shoots, films and full studios, with stars and licenses. CC0.

    GitHub · JavaScript · 130 stars · 23 forks · +3 stars in 24 hours · Trending score 1.61

  7. 7
    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.

    GitHub · TypeScript · 222 stars · 48 forks · 0 stars in 24 hours · Trending score 1.56

  8. 8
    pratikgx/local-ai-field-notes

    Notes from running AI on my own Mac mini: model speeds, what broke, the benchmark script, and people building local AI.

    GitHub · Python · 17 stars · 1 forks · +4 stars in 24 hours · Trending score 1.20

  9. 9
    sahibzada-allahyar/gliner2-ultrafast

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

    GitHub · Python · 81 stars · 9 forks · +2 stars in 24 hours · Trending score 0.72

  10. 10
    dougliell/Cheapsfield

    A 100% local, 100% open-weights creative studio for Windows: Higgsfield-style apps and a node canvas on ComfyUI + Comfy SDK. Sketch to packshot, product and architecture renders, AI influencers, character swap and 1080p video with sound. No cloud, no credits.

    GitHub · TypeScript · 10 stars · 4 forks · +1 stars in 24 hours · Trending score 0.46

  11. 11
    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.

    GitHub · Python · 43 stars · 10 forks · +1 stars in 24 hours · Trending score 0.45

  12. 12
    Trac-Systems/openmayhem

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

    GitHub · Rust · 20 stars · 2 forks · 0 stars in 24 hours · Trending score 0.38

  13. 13
    bojieli/checkpoint-forensics

    Read which GPU class initialised an open-weight LLM from its never-trained embedding rows. Independent replication and extension of Checkpoint Forensics.

    GitHub · Python · 12 stars · 4 forks · +1 stars in 24 hours · Trending score 0.37

  14. 14
    routerhubSI/deepseek-uncensored

    Every uncensored and abliterated DeepSeek build — V4.1 Flash 1017 Abliterated (the pinned, reproducible build that ranks third on the AA Cyber benchmark), V4 Pro, the tuned variants, abliterated GGUF builds and a cyber red-team prompt library. Maintained by RouterHub.

    GitHub · Python · 72 stars · 20 forks · 0 stars in 24 hours · Trending score 0.36

  15. 15
    HomoLapis/justae-flow

    ComfyUI inside the open-source EffectCraft. Your workflows, any model, on your timeline

    GitHub · TypeScript · 8 stars · 2 forks · 0 stars in 24 hours · Trending score 0.14

  16. 16
    nasser1941/lcode

    A coding agent that runs entirely on your own machine: open-weight models, up to 256K context, NVIDIA GPU or Apple Silicon Mac, via Ollama.

    GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.07

  17. 17
    yoel3imari/modelsift

    Find what open-weight Large Language Model (LLM) can fit into your hardware and run it

    GitHub · TypeScript · 12 stars · 3 forks · 0 stars in 24 hours · Trending score 0.06

  18. 18
    nhunsaker/screenshot-to-tokens

    Screenshot to Tokens: capture a running web app, SAM 3.1 segments the UI, Muse Spark names a tiered token set, verified rewrite to CSS variables, live Sorb preview. Meta Global AI Developer Hackathon 2026.

    GitHub · JavaScript · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.04

  19. 19
    routerhubSI/kimi-uncensored

    Every uncensored and abliterated Kimi build — Kimi K3.1 Pro Uncensored via API at 0.30/1.50 USD per million tokens, abliterated open-weight checkpoints for K3.1 Pro and K3, license notes and a red-team prompt library. Maintained by RouterHub.

    GitHub · 83 stars · 13 forks · 0 stars in 24 hours · Trending score 0.04

  20. 20
    Anil-matcha/awesome-uncensored-ai-image-models

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

    GitHub · 16 stars · 1 forks · 0 stars in 24 hours · Trending score 0.01

  21. 21
    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.

    GitHub · 30 stars · 5 forks · 0 stars in 24 hours · Trending score 0.01

  22. 22
    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.

    GitHub · 40 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  23. 23
    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

    GitHub · Python · 18 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  24. 24
    janishar/helmstudio

    A local launcher and platform for open-weight generative models. Install video, image and speech studios from their own repositories, run them on your Mac, and keep everything they make in one gallery.

    GitHub · Go · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00