
black-forest-labs/flux-kontext-max
Edit images via natural-language prompts. Provide an input image and an instruction, or omit the image to generate a new...
Found 69 models (showing 1-20)
Edit images via natural-language prompts. Provide an input image and an instruction, or omit the image to generate a new...
Edit images from text prompts. Provide an instruction and an optional input image to perform style transfer (watercolor,...
Edit images from a text prompt, preserving subjects, backgrounds, and fine details while making targeted changes. Provid...
Generate 1- or 4-view character turnarounds from a single input image, outputting one or multiple images. Control art st...
Generate images from text prompts with accurate text rendering, layout, and photorealism. Accept an optional image and m...
Edit images using text prompts. Input an image and a natural-language instruction to modify objects and attributes (colo...
Apply a reference image’s style to a new subject and generate an image guided by text and ControlNet. Takes a text promp...
Edit images by applying preset style transfers and semantic transformations to faces and dog faces using diffusion + CLI...
Convert images to Ghibli-style anime art. Accepts an image and a text prompt and outputs a stylized image; also supports...
Transform an input image into a Studio Ghibli–inspired, hand-drawn anime illustration. Accepts an image and an optional...
Convert face portraits into anime-style images. Input a cropped face photo and optionally select v1 or v2 style variants...
Convert photos to anime-style images. Takes an input image and outputs an anime-stylized image using selectable presets:...
Apply the style of a reference image to an input image. Provide a content image plus a style image and optionally a text...
Generate creepy cinematic cartoon–style images from text prompts or by restyling an input image. Accept an optional mask...
Stylize portrait photos into cartoon, comic, arcane, caricature, pixar, or illustration looks. Take a face image as inpu...
Generate images from text prompts. Condition outputs with reference inputs for content, style, and character, each with...
Generate stylized couples portraits from 1–2 identity images, guided by a text prompt, with optional base image, depth m...
Transform portraits into manhwa-style illustrations from an input image and an inpainting mask. Preserve subject identit...
Generate stylized portraits and avatars of a specific person from input photo(s) and a text prompt. Preserve identity us...
Generate sticker-style portraits from a face photo. Takes an image of a person and an optional text prompt to control st...