
stabilityai/stable-diffusion-3.5-large
Text-to-Image
โข
Updated
โข
167k
โข
โข
2.5k
Analyze images and videos with various tasks like captioning, detection, and OCR
Erase or change parts of images using masks
Generate images from text prompts
Apply the motion of a video on a portrait
Analyze images to generate captions, detect objects, or perform OCR
Upscale images to x4
High-fidelity Virtual Try-on
Image generator/identifier/reposer