MiniMax-H3-Image
Text-to-image and multi-image editing in 6 steps
Text-to-image and multi-image editing in 6 steps
Human-1M: 100K hours of sensorized human demonstrations
Multilingual TTS with voice cloning and steering controls
Generate images from text prompts using SplatAnything
Text-to-pixel-art diffusion LLM with live unmasking
Generative visual perception β segment, depth, normals
3D objects, each with the Python program that builds it
Minimax H3 Video in 2β4 Steps Without a VAE Decoder
A hands-on guide to training Mixture-of-Experts models
Which coding-agent harness should you use for your model?
generate a video from an image with a text prompt
Text-to-image and multi-image editing in 6 steps
Generate a video animation from a single image and prompt
Text-to-image and image editing, based on MiniMax-H3
Head swap with the BFS LoRA on Qwen-Image-2.1 (+turbo)
Talk face to face with LFM3-Omni, running in your browser
ltx 2.3 improved image-to-video with 10eros & native audio
One image to a 3D object (Gaussian splats)
Instant semantic search over pixel art, in your browser
Benchmarks and news on various repros of TypeSafe's Jev
Edit images with Qwen and enhance with FLUX.2 Klein
Generate 3D human motion from a video
Interactive Three.js 3D scenes from a prompt
Turbo, Relight, Camera, Face Swap, MOSS, Outpaint, Enhance
Uncensored Qwen-Image-2.1 generate + edit
Krea2 Turbo
text to video, image to video, video extend
Video generation with a synchronized soundtrack
High-fidelity 3D Generation from images
Uncensored Qwen 2.1 with All-In-One LoRAs
Image edit, text to image, image upscale, remove watermark
Semantic search for 3D assets: USD + RTX simulation previews