zer0int / CLIP-SAE-finetune
Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.
☆14Updated 4 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
- ☆24Updated last year
- finetune your florence2 model easy☆20Updated 8 months ago
- ☆28Updated 8 months ago
- Diffusers Implementation of Controlling Text-to-Image Diffusion by Orthogonal Finetuning☆35Updated last year
- Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (arXiv, 2024)☆50Updated 4 months ago
- [ECCVW 2024] Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models☆28Updated 3 months ago
- Custom LORA training on DynamiCrafter☆18Updated 9 months ago
- Let's try and finetune the OpenAI consistency decoder to work for SDXL☆24Updated last year
- ☆33Updated 5 months ago
- Tiny AutoEncoder for Hunyuan Video & Wan 2.1☆30Updated 3 weeks ago
- Pytorch implementation of Towards Consistent and Controllable Image Synthesis for Face Editing☆54Updated 2 months ago
- This repository shows how to use Q8 kernels with `diffusers` to optimize inference of LTX-Video on ADA GPUs.☆18Updated 3 months ago
- LoRA fine-tune directly on the quantized models.☆27Updated 5 months ago
- Explore how Flux Dev responds when you change the strengths of layers in the model.☆19Updated 7 months ago
- Gradio UI for training video models using finetrainers☆27Updated last week
- ☆25Updated 10 months ago
- Scripts to teach Flux the task of image editing from language with the Flux Control framework.☆69Updated last month
- (IA)^3 for Stable Diffusion☆34Updated 2 years ago
- Distilling Diversity and Control in Diffusion Models☆37Updated last month
- ☆46Updated 5 months ago
- ☆42Updated last year
- Model code for inferencing T5☆63Updated last month
- Official implementation of "VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis"☆19Updated 3 months ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆60Updated last month
- Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a…☆77Updated 6 months ago
- Fine-tune of Florence-2 for shot categorization.☆24Updated last month
- Public code release for the paper "ProCreate, Don’t Reproduce! Propulsive Energy Diffusion for Creative Generation"☆37Updated 5 months ago
- ☆22Updated 6 months ago
- ☆18Updated 7 months ago
- ☆17Updated last year