training-free repositories

Trending repositories tagged training-free, ranked by trending score. Updated daily.

  1. 1
    DSL-Lab/UniEdit-Flow

    [ICLR 2026] UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models

    GitHub · Python · 54 stars · 5 forks · +1 stars in 24 hours · Trending score 0.45

  2. 2
    shjo-april/Chain-of-Prompts

    [Under Review] Chain-of-Prompts (CoP): One Click per Cell Type Suffices, Training-free Group Interaction for Cell Instance Segmentation

    GitHub · Jupyter Notebook · 11 stars · 2 forks · 0 stars in 24 hours · Trending score 0.14

  3. 3
    MaximilianLindholz/weight-space-programming-medical

    Weight-Space Programming for Medical Imaging (arXiv:2611.12066): LLMs (Claude Opus, GPT) write the weights of medical image classifiers directly — no training data, no gradient descent. MedMNIST + SynthUterus.

    GitHub · Python · 6 stars · 1 forks · 0 stars in 24 hours · Trending score 0.08

  4. 4
    wwj-code/OAVC

    Object-Aware Background-Controlled Editing via Weighted Velocity Guidance (training-free image and video editing)

    GitHub · Python · 11 stars · 0 forks · 0 stars in 24 hours · Trending score 0.06

  5. 5
    zylwithxy/HRDiT

    [ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models"

    GitHub · Python · 317 stars · 3 forks · 0 stars in 24 hours · Trending score 0.00

  6. 6
    pixelchemy-research/TRACE

    [ACCV 2026] TRACE: Time-Adaptive Residual Attention Control with Content–Style Decomposition for Training-Free Diffusion Style Transfer

    GitHub · Python · 10 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  7. 7
    nick7nlp/RAZOR

    RAZOR: Pruning Replaceable Experts in LLMs — training-free expert pruning for Mixture-of-Experts (MoE) models, with the MoECal calibration corpus

    GitHub · Python · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00

  8. 8
    Archerkattri/fast-trellis2

    TaylorSeer (Fast) baseline acceleration for TRELLIS.2-4B.

    GitHub · Python · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00