Qwen Qwen3.5 397B A17B
Generate text with Qwen 3.5 model via Novita API
Image edit, text to image, image upscale, remove watermark
Edit image camera angle with interactive 3D controls
Upscale images and videos to 4K quality
Audio Conditioned LipSync with Latent Diffusion Models
Generate art prompts and style tags from any image
Generate a short video with audio from an image and prompt
Generate Hollywood Style Actors on your Local Machine
Text-to-3D and Image-to-3D Generation
Display text leaderboard
Browse and view model judgments in benchmarks