LAION-AI / Discord-Scrapers
Implementation of a discord channel scraper to generate datasets.
☆58Updated 3 months ago
Related projects: ⓘ
- This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.☆149Updated 10 months ago
- ☆0Updated 9 months ago
- Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a…☆67Updated 2 weeks ago
- Web page with political compass quiz results for open LLMs☆37Updated 7 months ago
- ☆49Updated last year
- ☆25Updated 9 months ago
- ☆53Updated 4 months ago
- ☆26Updated last year
- ☆78Updated 8 months ago
- AniPortrait with Gradio: Audio-Driven Synthesis of Photorealistic Portrait Animation☆21Updated 5 months ago
- Official Implementation of weights2weights☆98Updated last week
- An AI focused photo manipulation tool based on Gradio☆126Updated this week
- Experimental sampler to make LLMs more creative☆29Updated last year
- ☆33Updated this week
- (Windows/Linux) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on python (Gradio interface). Translated on 3 lang…☆37Updated this week
- ☆30Updated last year
- ☆58Updated this week
- sd3 dreambooth lora training book, adapted from the diffusers doc☆40Updated 3 months ago
- [inactive] MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation☆13Updated 4 months ago
- ☆22Updated 7 months ago
- Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"☆84Updated 8 months ago
- Community ComfyUI workflows running on fal.ai☆53Updated 3 weeks ago
- Gradio UI for a Cog API☆62Updated 5 months ago
- Doohickey is a stable diffusion tool for technical artists who want to stay up-to-date with the latest developments in the field.☆39Updated last year
- ☆23Updated 3 months ago
- A multimodal inference pipeline that integrates InstructBLIP with textgen-webui for Vicuna and related models.☆30Updated last year
- Pipeline to scrape prompt + image url pairs from LAION `share-dalle-3` discord channel☆11Updated 11 months ago
- Faster LCM is a script which enables to transfer image styles at 45fps with RTX4090, 33fps with A100.☆93Updated 9 months ago
- Diffusion Reinforcement Learning Library☆171Updated 7 months ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆48Updated last month