Artifacts

Builds a 3D mesh from a single image in about ten seconds, using the InstantMesh model.

Restyles an image in a Studio Ghibli look using the EasyControl Ghibli model.

Generates images that keep the identity of a face in your uploaded photo.

Expands a short idea into a longer, more detailed Stable Diffusion prompt.

Animates a single picture into a short video with Stable Video Diffusion.

Quick text-to-image generation with the Z-Image Turbo model.

Official demo of the Stable Diffusion 3 Medium text-to-image model.

Builds detailed text-to-image prompts for FLUX from a few chosen options and keywords.

Generates descriptive captions of images for training data or prompts.

Virtual try-on tool that puts a garment onto a person photo using the OOTDiffusion model.

Writes descriptive captions for images in several styles such as descriptive or training-prompt format.

Official demo for generating and editing images with FLUX.2 dev.

Turns a face photo into an anime-style image with AnimeGANv2.

Quickly reconstructs a textured 3D asset from one image.

Generates sound effects that fit a video clip or a text prompt.

Generates a high-detail colored 3D model with about a million faces from a single image.

Creates 3D assets from images using a scalable 3D generation model.

Generates images from a text prompt with FLUX, updating the result in near real time as you type.

Builds a detailed 3D geometry model from a single view image.

Generates custom images from a text prompt combined with one or more reference images.

Generates images from text in real time using SDXL Lightning.

Runs Microsoft Florence-2 for captioning, object detection and OCR on a single image.

Describes an uploaded image as a text prompt you can reuse in an image generator.

Extends an image outward with FLUX Fill, guided by a prompt.