MiniMax H3 Ref2VA Studio Unrestricted
MiniMax H3 video with image references and audio
MiniMax H3 video with image references and audio
Text-to-image and image editing, based on MiniMax-H3
Talk face to face with LFM3-Omni, running in your browser
One image to a 3D object (Gaussian splats)
Six-step video + audio · Pika reference code
Real-time t2i & editing with a Qwen-Image-2.1 2-step LoRA
Realistic Air speech and voice cloning with Audio8 0.6B
Open weights for image editing, generation and layouts
Fibo 2.0 Edit Turbo image editing in 4 steps
Text-to-speech that runs in your browser
Image to high-res 3D mesh with Hi3Dv1 refinement
FastVideo 8-step video+audio from image/video/audio refs
MOSS-Image text-to-image as a gr.Workflow node canvas.
Krea 2 Turbo text2image and image editing
NVIDIA Nemotron Transcribe Demo
6-step Qwen-Image-2.1, T2I + editing, vs-base comparison
Create songs, arrange vocals, and remix music with StepFun
4-step text-to-video+audio with MiniMax-H3 FlashGen LoRA
Fast Wan 2.2 image-to-video with first/last frames
High-quality voice cloning TTS for 600+ languages
High-fidelity 3D Generation from images
Image-to-3D Generation
generate a video from an image with a text prompt
Scalable and Versatile 3D Generation from images
Upgraded to v1.0!
A JSON spec and renderer for interactive agent avatars
Free, open-source 3D sculpting for Linux, macOS and Windows: dense meshes, remeshing, painting, built-in AI (image/text…
Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.
Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows…
Generative Fill, Remove object, Generative Expand and Text to Image for PhotoCraft and GIMP 3. Free, local, on your own…