Search the full model catalog.

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.

Moondream 3 Preview Detect takes an image and a short text description and returns a bounding box for each matching object, as normalized x_min, y_min, x_max and y_max values in JSON.

Name an object and Moondream 3 Preview returns one normalized x, y point for each match, as JSON you can count or draw as markers on the image.

Moondream 3 Preview writes a prose caption for an image. There is no prompt: you choose Short, Normal or Long and the model decides what to describe.

Ask Moondream 3 Preview a question about one image and get the answer as text or JSON. A reasoning step runs by default and can be switched off for simple questions.

Ovi generates a short video and its soundtrack together from a text prompt and an optional first-frame image, with spoken lines you write between speech tags.

OpenAI's smaller open-weight reasoning model, a mixture-of-experts with 21B parameters (3.6B active) under Apache 2.0, served here as a text chat model with per-session history.

A single Wiro form for HiDream-I1: pick the Full, Dev or Fast checkpoint from a dropdown and generate images from a text prompt with one shared settings panel.

A guidance-distilled checkpoint of the 17B HiDream-I1 text-to-image model, trained from Full and set up for 28 sampling steps with guidance off and a flow shift of 6.0.

Reads a batch of employee pulse surveys and returns JSON for each file with its main themes, requests and a positive and negative sentiment split, plus batch averages, in English or Turkish.

Scores a candidate's completed culture fit questionnaire against the culture you describe and backs each score with a quote from the candidate's answers.

Drafts a culture fit questionnaire for job applicants from a paragraph about your company, optionally drawing on your culture or about page as well.

Qwen-Image-Edit edits an image from a text instruction. Built on the 20B Qwen-Image model, it adds, removes or replaces objects and edits Chinese or English text inside the image.

Upscales an image up to 4x: FLUX.1 [dev] redraws fine detail while Jasper's upscaler ControlNet holds the layout of the original. Output tops out at 1920 pixels on the longest side.

Generates a video that morphs one image into another: you set the first and last frames plus a short prompt, and PixVerse v3.5, v4, v4.5 or v5 fills in the motion between them.

Animates one photo with a preset PixVerse effect, either a tiger wrapping its paws around the subject or a zombie makeover of the face, on PixVerse's v4.5 image-to-video model.

Qwen3-30B-A3B-Thinking-2507 reasons before every answer, and its thinking runs longer than in the original Qwen3-30B-A3B. Qwen recommends it for highly complex reasoning tasks.

Qwen3-32B is Qwen's 32.8B dense model. It reasons step by step by default and answers directly on request, and on Wiro it can call your functions or return a JSON object.

A Qwen3 mixture-of-experts model (30.5B total, 3.3B active) that reasons in a think block or answers directly, chosen turn by turn. On Wiro it accepts function definitions and can return JSON.

A Qwen3-Coder mixture-of-experts model for everyday programming, with 3.3B of its 30.5B parameters active per token. It runs in non-thinking mode only, so each reply starts with the answer.