Qwen2.5-Coder-32B-Instruct Serverless
Qwen2.5-Coder-32B-Instruct, no GPU required
Qwen2.5-Coder-32B-Instruct, no GPU required
New SOTA smol king by Hugging Face
The best open source reasoning model, no GPU required
base model for mono-channel completion
Realtime Image/Video Gen AI Arena
Paligemma2 Detection with Supervision
Display code snippets for different chat providers
A model for classifing a video to having violence or not
Find similar images from a collection
Detect and annotate poses in images and videos
Chat with Mini-Omni 2 - powered by Gradio and WebRTC ⚡️
Create expressive talking head videos with custom audio and poses
Generate bounding boxes and text for image objects
Controlling Computers with Small Models
A unified multimodal understanding and generation model.
Process and redact videos based on prompts
Generate responses to video or image inputs
Answer questions about videos using text
Generate depth maps from images
Engage in conversations with a smart AI assistant
Aligned Monocular Depth Estimation for Dynamic Videos
Video Dubbing with Open Source Projects
Generate video content from a topic
Interact with the Aya family of models.
Convert and edit media files