zer0int / CLIP-SAE-finetune
Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.
☆13Updated 3 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
- finetune your florence2 model easy☆20Updated 8 months ago
- ☆24Updated last year
- TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder☆53Updated 2 months ago
- ☆27Updated 7 months ago
- Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (arXiv, 2024)☆50Updated 4 months ago
- ☆25Updated 9 months ago
- Diffusers Implementation of Controlling Text-to-Image Diffusion by Orthogonal Finetuning☆35Updated last year
- ☆41Updated last week
- A comprehensive codebase for training and finetuning Image <> Latent models.☆30Updated 3 weeks ago
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆73Updated 3 weeks ago
- Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a…☆77Updated 5 months ago
- ☆46Updated 4 months ago
- Pytorch implementation of Towards Consistent and Controllable Image Synthesis for Face Editing☆52Updated last month
- Modern Stable Diffusion models family - Fluently☆29Updated 9 months ago
- ☆32Updated 4 months ago
- Fine-tune of Florence-2 for shot categorization.☆22Updated 3 weeks ago
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!☆89Updated 3 weeks ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆59Updated 2 weeks ago
- Public code release for the paper "ProCreate, Don’t Reproduce! Propulsive Energy Diffusion for Creative Generation"☆37Updated 4 months ago
- (IA)^3 for Stable Diffusion☆35Updated last year
- Scripts to teach Flux the task of image editing from language with the Flux Control framework.☆60Updated this week
- ☆13Updated last year
- Scale-wise Distillation of Diffusion Models☆60Updated this week
- Official implementation of "Perturbed-Attention Guidance"☆55Updated 8 months ago
- Gradio UI for training video models using finetrainers☆26Updated this week
- [ECCV 2024] BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion☆20Updated 8 months ago
- Minimal Differentiable Image Reward Functions☆51Updated 3 weeks ago
- LoRA fine-tune directly on the quantized models.☆27Updated 4 months ago
- Model code for inferencing T5☆62Updated 2 weeks ago
- Animatediff implementation. Includes a ControlNet pipeline.☆19Updated last year