zer0int / CLIP-SAE-finetuneLinks
Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.
☆16Updated 8 months ago
Alternatives and similar repositories for CLIP-SAE-finetune
Users that are interested in CLIP-SAE-finetune are comparing it to the libraries listed below
Sorting:
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆100Updated 6 months ago
- Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a…☆80Updated 10 months ago
- ☆128Updated 11 months ago
- Model code for inferencing T5☆66Updated 6 months ago
- Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (ICCV, 2025)☆52Updated 2 months ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆62Updated 6 months ago
- finetune your florence2 model easy☆20Updated last year
- ☆24Updated last year
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆81Updated last year
- Enhancing Motion Dynamics of Image-to-Video Models via Adaptive Low-Pass Guidance (arXiv 2025)☆48Updated last month
- This repository provides a minimal, single-file implementation of SingLoRA (Single Matrix Low-Rank Adaptation) as described in the paper …☆42Updated this week
- Official PyTorch Implementation for the "Recovering the Pre-Fine-Tuning Weights of Generative Models" paper (ICML 2024).☆86Updated 5 months ago
- ☆45Updated 9 months ago
- TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder☆57Updated 7 months ago
- ☆32Updated 10 months ago
- This is the official implementation of "T-LoRA: Single Image Diffusion Model Customization Without Overfitting"☆121Updated 2 months ago
- ☆69Updated 11 months ago
- ☆28Updated last year
- Inference-time scaling of diffusion-based image and video generation models.☆168Updated 2 months ago
- Gradio UI for training video models using finetrainers☆31Updated 4 months ago
- Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"☆86Updated last year
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆118Updated 6 months ago
- Home Made Diffusion Models☆131Updated this week
- A comprehensive codebase for training and finetuning Image <> Latent models.☆44Updated 6 months ago
- stochastic bfloat16 based optimizer library☆19Updated 9 months ago
- Scale-wise Distillation of Diffusion Models☆108Updated 2 months ago
- Official Implementation for paper: Negative Token Merging: Image-based Adversarial Feature Guidance☆75Updated 2 months ago
- Distilling Diversity and Control in Diffusion Models☆43Updated 4 months ago
- Modern Stable Diffusion models family - Fluently☆32Updated last year
- Official implementation of "Single Image Iterative Subject-driven Generation and Editing".☆99Updated 3 months ago