MiniMax H3
Video generation with a synchronized soundtrack
Video generation with a synchronized soundtrack
Multilingual CPU-only ASR with a 1.58-bit BitNet decoder
Multi-view character sheet from one image (FLUX.2 LoRA)
Route prompts with LFM2.5 Encoder on CPU
Unquantized MiniMax-H3 from image, audio, video refs
Bilingual EN/KO speech LM - transcribe, ask, and speak
Chat with Laguna S 2.1 model in a terminalβstyle web interface
Detailed image background removal with open weights.
Generate a video from an image with custom animation
Demo of the Collection of Qwen Image Edit LoRAs
Wan2.2 I2V Blink Effect
generate a video from an image with a text prompt
Video generation with a synchronized soundtrack
Demo of the Collection of Qwen Image Edit LoRAs
Chat with DeepSeekβV4βFlash model via OpenAIβcompatible API
Image edit, text to image, image upscale, remove watermark
Multi-view character sheet from one image (FLUX.2 LoRA)
ltx 2.3 improved image-to-video with 10eros & native audio
High-fidelity 3D Generation from images
Codec-native video & image understanding with Mage-VL 4B
Single-image Gaussian reconstruction
Live interactive world rollout from an image
Use multiple FLUX.2-Klein LoRAs
Powerful image editing - supports one or two input images.
Run complete 3.96M and 9.36M text-to-waveform models live.
Unquantized MiniMax-H3 from image, audio, video refs
Generate high-quality images from text prompts in seconds
Extract text from images and PDFs instantly
text to video, image to video, video extend
FireRed-Image-Edit Γ Qwen-Image-Edit-Rapid (Transformers)
Multilingual CPU-only ASR with a 1.58-bit BitNet decoder
Run an on-device LFM2.5 research agent with WebGPU