google/gemma-3-270m
Text Generation β’ 0.3B β’ Updated β’ 6.64M β’ 1.04k
Replace objects in images using prompts or reference images
On Device Large Action Models to plan and execute tasks
Fill and edit images using masks
Inpaint images with text prompts and custom masks
Easily expand image boundaries
Import a portrait, click to move the head!
Generate custom images using mixed FLUX LoRA adapters
Efficient T2V generation
Official Demo of Lotus (https://lotus3d.github.io/)
Generate music from text descriptions
Generate customized images from text and reference photos
Generate spoken audio from text using Edge TTS