TRELLIS.2
High-fidelity 3D Generation from images
High-fidelity 3D Generation from images
Decompose an image into layers and export as PPTX or ZIP
Use natural language to solve fun physics simulation puzzles
Sharp Monocular View Synthesis in Less Than a Second
Convert images to 3D models and depth maps
Molmo2 - Image, Video (QA, Pointing & Tracking)
Generate text variants guided by brain patterns
๐ Support the blending of 2-6 Images!
High-fidelity 3D Generation from images
Decompose an image into layers and export as PPTX or ZIP
Image edit, text to image, face swap, image upscale
Generate images from text prompts
Wan2.2 Animate
generate a video from an image with a text prompt
Chatterbox Turbo Demo
Generate edited images based on a prompt and input image
Generate LoRA from a single image
Generate images from text prompts
Use natural language to solve fun physics simulation puzzles
The secrets to building world-class LLMs
Fast 4 step inference of Qwen Image Edit 2511
Demo of the Collection of Qwen Image Edit LoRAs
Generate any application by Vibe Coding
generate a video from an image with a text prompt
Create images from text and optional images
generate a video from an image with a text prompt
Fast 4 step inference with Qwen Image Edit 2509
Sharp Monocular View Synthesis in Less Than a Second
Explore the Eiffel Tower Llama experiment with open-source models
Generate custom voices with text and instructions
fast video generation with Wan 2.2 using rCM
Generate expressive voice from text using audio reference