Search the full model catalog.

Puts the person from your photo in a vertical scene with a music player card showing a YouTube track's title, then plays that track under the image as a short video.

Seedream 4.5 is ByteDance's image generation and editing model. It works from a prompt and up to 14 reference images, keeps faces, lighting and color tone from the references, and outputs at 2K or 4K.

FLUX.2 [dev] is a 32 billion parameter rectified flow transformer from Black Forest Labs that generates, edits and combines images from text instructions, with up to 5 reference images per run.

Z-Image Turbo is the distilled, lighter variant of Tongyi-MAI's 6B-parameter Z-Image family. It turns a text prompt into photorealistic images and can write English and Chinese text inside them.

Black Forest Labs' FLUX.2 [flex] generates and edits images from a prompt and up to 8 reference images, and lets you set steps and guidance yourself. It is specialized for legible text and small details.

FLUX.2 [pro], from Black Forest Labs, generates images from a prompt or edits and combines up to 8 reference photos in one request. Width and height are set in pixels, up to 2048 each.

Create store-ready promo images from your real app screenshots. Pick Apple App Store or Google Play, then control background gradients, font, and text color.

Animates a pet photo into a short dance clip, or puts a person and their pet together in a karate, kung-fu or sports training scene. Built on Seedream V5 Lite with Seedance 1.0 Pro or Wan 2.2.

Pruna VACE is Pruna AI's optimized build of VACE, the all-in-one video model from Alibaba's Tongyi Lab. It makes clips of up to 81 frames at 480p or 720p, with up to 3 reference images to keep characters consistent.

Google's Gemini 3 Pro Image (Nano Banana Pro) creates and edits images at 1K, 2K or 4K from a prompt and up to 14 references, aimed at legible text, charts and dense layouts.

Qwen Image Edit Plus is the Qwen team's multi-image editing model, offered here by Pruna. It edits one photo from a written instruction or merges people and objects from two photos into one scene.

Wan Image Small is a smaller text-to-image model that Pruna offers for prototyping and large batches. It returns one still per prompt and adds a 21:9 widescreen frame to the usual aspect ratios.

P-Image-Edit is Pruna's image editing model. You upload one to five photos and describe the change in plain words, from a new wall material to a beach cleared of people.

P-Image is Pruna's own text-to-image model. Pruna documents it for exact prompt adherence and for writing requested words into the picture. Each request returns one image in one of seven aspect ratios.

Restages one photo of a person, couple or pet as a styled social post, often a multi-shot strip or grid. Its 200-plus presets, from digicam looks to ski slopes, run on Nano Banana Pro, Seedream V5 Lite or GPT Image 2.

Camera Angle Editor redraws an existing photo from a new viewpoint, such as a back view, a side profile, top-down or a 45° three-quarter angle, keeping the same subject and setting.

The lighter variant of MiniMax Hailuo 2.3, for image-to-video only. You give it a first frame and an optional prompt, and it returns a 6 or 10 second clip with the image's proportions.

MiniMax's follow-up to Hailuo 02, for text-to-video and image-to-video. MiniMax reports more natural body movement and facial micro-expressions in this release.

DreamOmni2 edits or composes images from a text instruction plus up to four input pictures. A reference can supply a subject, like a jacket or a pet, or an abstract trait such as a print or a painting style.

Save time and production costs with AI Product Photoshoot. Generate polished product images featuring adaptive lighting, varied angles, and contextual scenes. Ideal for online stores, marketing teams, and agencies looking to accelerate content creation with consistent, high-quality visuals.