Store

[NVIDIA GPU ONLY] One click installer for Intel's ldm3d

Dense Text-to-Image Generation with Attention Modulation

An open source implementation of Microsoft's VALL-E X zero-shot TTS model

Demo showcasing ~real-time Latent Consistency Model pipeline with Diffusers and a MJPEG stream server (https://github.com/radames/Real-Time-Latent-Consistency-Model)

Demo showcasing ~real-time Latent Consistency Model pipeline with Diffusers and a MJPEG stream server (https://github.com/radames/Real-Time-Latent-Consistency-Model)

Text-to-Video (T2V) generation framework from Vchitect https://github.com/Vchitect/LaVie

An AI powered mirror

A Realtime Creation Engine

Integrates Florence2 and SAM2 models for detailed image captioning and object detection. Florence2 generates detailed captions that are then used to perform phrase grounding. The Segment Anything Model 2 (SAM2) converts these phrase-grounded boxes into masks. https://huggingface.co/spaces/SkalskiP/florence-sam

Stable Diffusion web UI UX: https://github.com/anapnoe/stable-diffusion-webui-ux

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation:https://github.com/Zejun-Yang/AniPortrait

Langflow is a dynamic graph where each node is an executable unit. Its modular and interactive design fosters rapid experimentation and prototyping, pushing hard on the limits of creativity: https://github.com/langflow-ai/langflow

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding/ https://github.com/Tencent/HunyuanDiT

Your image is almost there!:https://github.com/lllyasviel/Omost

Drag & drop UI to build your customized LLM flow: https://github.com/FlowiseAI/Flowise

[Need 24GB VRAM] Cambrian-1 is a family of multimodal LLMs with a vision-centric design: https://github.com/cambrian-mllm/cambrian

Dough is a open source tool for steering AI animations with precision

moondream1 is a tiny (1.6B parameter) vision language model trained by @vikhyatk that performs on par with models twice its size. It is trained on the LLaVa training dataset, and initialized with SigLIP as the vision tower and Phi-1.5 as the text encoder. https://huggingface.co/spaces/vikhyatk/moondream1