A unified multimodal understanding and generation model.
The Ultimate Anime-themed SDXL model
EscapeExpress : LLM AI detective puzzle game.
Ranking of LLMs for agentic tasks
Generate depth video from input video
Text-to-3D and Image-to-3D Generation
Fast and free uncensored chatbot that just works.
Make Custom Voices With KokoroTTS
Generate responses using images and text input
Communicate with a multimodal chatbot
Find matching images from a collection
FitDiT is a high-fidelity virtual try-on model.
Detect and annotate poses in images and videos
3D generation from sketchs with TRELLIS & sdxl
Gaze detection using Moondream
Transform research papers and mathematical concepts into stu
Audio Conditioned LipSync with Latent Diffusion Models
✨[With v1.0.0] Accelerated TTS on Kokoro-82M
Extract clothing from images using a mask
https://huggingface.co/papers/2501.03006