Visualize patch similarity with DINOv3 feature maps.
Generate images from text prompts
Zero Shot Object Detection
Explore 3D worlds by selecting examples or uploading files
Generate high-quality videos from text prompts and images
One-minute creation by AI Coding Autonomous Agent 'MOUSE-I'
Use hugging face's new smollm3
Unified MLLM with Text-Aligned Representations
relight images with Flux Kontext[dev]
edit images with Kontext and LoRAs
OmniGen2: Unified Image Understanding and Generation.
Kontext image editing on FLUX[dev]
Bytedance Seedance T2V/I2V Free VIDEO geerator
Next-Gen High-Resolution 3D Model Generation