sayakpaul / caption-upsamplingLinks
This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.
☆153Updated last year
Alternatives and similar repositories for caption-upsampling
Users that are interested in caption-upsampling are comparing it to the libraries listed below
Sorting:
- SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.☆177Updated last year
- Implementation of HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models☆174Updated last year
- ☆320Updated 9 months ago
- ☆128Updated 8 months ago
- ☆431Updated last year
- Official PyTorch codes for the paper: "ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation"☆244Updated last year
- Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"☆86Updated last year
- ☆118Updated 2 years ago
- ☆86Updated 2 years ago
- Official Implementation of 'Inserting Anybody in Diffusion Models via Celeb Basis'☆254Updated last year
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆424Updated last year
- A diffusers based implementation of HyperDreamBooth