Smart Character Swap - FLUX.2 Klein
Occlusion-aware character & face swap with FLUX.2 [klein]
Occlusion-aware character & face swap with FLUX.2 [klein]
Video generation with a synchronized soundtrack
Powerful image editing - supports one or two input images.
WAN2.2 based I2V
generate a video from an image with a text prompt
4-step image generation and editing with LLaDA-Image
Restore and enhance faces in photos with optional upscaling
Generate music from a text description and optional melody
Convert any voice to match another speaker instantly
Remove/Change background of video.
Audio Conditioned LipSync with Latent Diffusion Models
Text-to-3D and Image-to-3D Generation
A unified multimodal understanding and generation model.
Generate custom captions, tags, or prompts for any image
Image-to-3D Generation
Demo of the Collection of Qwen Image Edit LoRAs
Text-Guided Object Manipulation Using Qwen Image Edit + LoRA
Upscale videos to 2x or 4x higher resolution
Edit image camera angle with custom 3D controls
Generate or edit images from text prompts
Music Generation Foundation Model v1.5
Multi-task image generator with dynamic, chainable workflows
One-click model liberation + chat playground
generate a video from an image with a text prompt