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 terminal‑style 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
Video generation with a synchronized soundtrack
Wan2.2 I2V Blink Effect
Demo of the Collection of Qwen Image Edit LoRAs
Chat with DeepSeek‑V4‑Flash model via OpenAI‑compatible API
generate a video from an image with a text prompt
Multi-view character sheet from one image (FLUX.2 LoRA)
Image edit, text to image, image upscale, remove watermark
ltx 2.3 improved image-to-video with 10eros & native audio
Use multiple FLUX.2-Klein LoRAs
Unquantized MiniMax-H3 from image, audio, video refs
High-fidelity 3D Generation from images
Single-image Gaussian reconstruction
Powerful image editing - supports one or two input images.
Generate high-quality images from text prompts in seconds
text to video, image to video, video extend
FireRed-Image-Edit × Qwen-Image-Edit-Rapid (Transformers)
Codec-native video & image understanding with Mage-VL 4B
Live interactive world rollout from an image
Route prompts with LFM2.5 Encoder on CPU
Ultra-fast local NVFP4 video + synchronized audio generation
Run an on-device LFM2.5 research agent with WebGPU
Demo of the Collection of Qwen Image Editing LoRAs