Search the full model catalog.

Reads a batch of CVs and writes a plain-text profile of each candidate in English or Turkish, from one paragraph up to three.

PixVerse's May 2025 model and its last 4.x release, turning text into clips of 5 or 8 seconds at resolutions up to 1080p. PixVerse launched it promising smoother handling of complex movement.

PixVerse V4 animates a still image, kept as the first frame, for 5 or 8 seconds at 360p to 1080p. It sits between V3.5 and V4.5 and fits projects where new shots must match existing V4 footage.

PixVerse's February 2025 video model, used here to turn a text prompt into a 5- or 8-second clip at up to 1080p. Its launch post promised better realism and more natural movement.

PixVerse's text-to-video model from December 2024, making 5- or 8-second clips at up to 1080p. Of V3.5, V4 and V4.5, it is the only one on which the anime, clay, comic, 3D animation and cyberpunk presets work.

PixVerse V4.5 generates video from one photo and a text prompt, at 360p to 1080p and 5 or 8 seconds per clip. It is the newest of the V3.5, V4 and V4.5 image-to-video versions and shares their controls.

PixVerse V3.5 turns a still image and a text prompt into a clip of 5 or 8 seconds. Among V3.5, V4 and V4.5, it is the version where the anime, 3D animation, clay, comic and cyberpunk style presets take effect.

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language

Combines three uploaded pictures into one scene with FLUX.1 Kontext [dev], for example two characters and the room they should sit in, arranged the way your prompt describes.

Places something from one photo into another with FLUX.1 Kontext [dev]. Upload a scene and a second picture, such as a toy dog or a stone texture, and say in the prompt where it belongs.

Edits one photo from a written instruction using Black Forest Labs' FLUX.1 Kontext [dev]. Ask it to remove a parked car or add rain, and the parts of the picture you did not mention are left as they were.

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language.

Gen-4 Turbo from Runway animates one still image into a 5 or 10 second video at 24 fps. Your image becomes the first frame, and the prompt only has to describe the motion.

MiniMax's second-generation Hailuo model turns a first frame, and an optional last frame, into a clip of 6 seconds at up to 1080P or 10 seconds at 768P.

MiniMax's Hailuo 02 in text-to-video mode. It renders native 1080p clips of 6 seconds or 768p clips of 6 or 10 seconds, and can rewrite short prompts with its prompt optimizer.

Recolors a photo with one of six looks: Vivid, Black and White, Sepia, Grayscale, Warm or Cool. The subject and framing of the picture stay as they were.

Repairs cracked or faded old photos and returns them in color. There is no prompt: you upload one image and the app redraws it.

Create polished professional headshots instantly. Our image-to-image AI refines your photos into high-quality headshots, ensuring a crisp, professional, and confident look. Perfect for résumés, LinkedIn, and corporate profiles.

Generates an action or fantasy scene, such as a moonwalk or a volcano expedition, around the person in a photo and drops the original background. There are 32 scenarios, with Random as the default.

Places the person from your photo at one of 66 named locations, such as the Eiffel Tower or Machu Picchu, in the same clothes and roughly the same pose. The location list starts on Random.