Everything in the catalog

Enlarges images in tiles with a Stable Diffusion based upscaler to add fine detail.

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.

Upscales low-quality images with a FLUX ControlNet model.

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

Converts text to natural-sounding speech using the StyleTTS 2 model.

Upload a screenshot of a web page and get HTML that approximates it.

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

Generates music from text prompts using the ACE-Step music generation foundation model.

Transcribes audio files or microphone input with the Whisper large-v3 model.

Rewrites AI-generated text so it reads more like human writing, with no sign-up needed.

Turns text into speech with MeloTTS, a multilingual text-to-speech model.

Syncs a speaker's lip movements in a video to a new audio track using latent diffusion.

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

Generates images from text in real time using SDXL Lightning.

Earlier BRIA background removal model in a simple upload-and-cut-out demo.

Checks whether text looks AI-written, with sentence-level analysis and no sign-up.

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.

Creates a short music sample inspired by the mood of an image you provide.

Reads text from images with a choice of OCR models, including olmOCR and Qwen2-VL-OCR.

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

Generates 3D objects from a text prompt or a single image using Shap-E.