All creative tools

Upload a reference and ask the Agent to turn what it can see into a complete image prompt. Separate the subject, composition, light and visual treatment so you can reuse the parts that matter. This is a new description of the image, not recovery of its original prompt or seed.

What you provide

An uploaded or selected reference image, the features to preserve, and your preferred prompt language or format.

What you get

A complete reusable prompt, visible composition and style notes, and any uncertain details. Generate a new image only when you request it.

Turn a process, comparison or short set of facts into an infographic with a clear reading order. The Agent organizes the supplied content, plans the modules and writes exact labels before generating the visual. Review every number and word before sharing.

What you provide

Source text, verified figures and units, audience, required labels, and a preferred layout or aspect ratio.

What you get

An infographic plan and prompt, plus a generated image when requested. Editable documents require a separate supported export.

Create an ordered set of social cards for a tutorial, product explanation or article summary. The Agent plans one message per page, keeps shared colors and typography, and generates individual images when asked. You review and publish the finished material yourself.

What you provide

A topic or source text, audience, page count, aspect ratio, brand colors and any exact wording.

What you get

An ordered copy outline, complete page prompts, and separate generated images when requested. Posting is not included.

Use the Agent to edit a draft that sounds repetitive, vague or overly formal. The humanizer workflow checks concrete wording problems while preserving facts, qualifications and the author’s voice. It is an editing aid, not an AI detector or a guarantee of a detector score.

What you provide

The original draft, the intended audience and tone, plus optional samples of your own writing.

What you get

A revised draft that keeps the original meaning and protected details. Ask for edit notes or a supported document export if needed.

Discuss the audience, message and visual direction before creating. The assistant can work with reference images and supported documents, research the web, generate images and export documents in the same conversation. It also supports outfit design, clothing breakdown images, virtual try-on and multi-angle looks.

What you provide

A goal or question, optional reference images and supported documents.

What you get

A creative plan, answers with source links when researched, images or downloadable documents.

Attach a video in the assistant and ask what you want to understand. The assistant uses mimo-v2.6-flash to inspect the actual video, then answers with observations and uncertainty where details are unclear.

What you provide

MP4, MOV, AVI or WMV, up to 180 MB per video, and a question.

What you get

A text summary, scene observations or answers with approximate timestamps when requested.

Create product scenes, posters, illustrations and character concepts from a written brief. Add references when a subject or visual direction matters, or start from a complete editable template.

What you provide

A text prompt, optional reference images, model and supported output settings.

What you get

Generated still images for preview, download, editing or use on a canvas.

Use a reference image for a new variation, or paint a mask to describe a local change. Tell the model what to replace and what to preserve, then review the new version against the original.

What you provide

A source image, an edit instruction and a mask for local changes.

What you get

A new image version that can be downloaded or used for another edit.

Build on a finite canvas with photos, generated accessories, editable text and shapes in separate layers. The assistant analyzes the whole composition, edits across layers and adds or refines elements in stages, checking the actual composite after each saved step.

What you provide

Uploaded images or layered files, existing private generated images, text and editing instructions.

What you get

Editable private projects, transparent PNG, JPEG, WebP, SVG, PDF, PSD and Compositor-compatible packages.

Compare how available image models interpret one brief. Keep the prompt and references consistent, then inspect the results side by side to choose a direction for the next edit.

What you provide

One prompt, optional references and a selection of available models.

What you get

Separate image results labelled by model.

One creation form accepts your brief and images. Images can guide people, scenes or an ordered progression. Review the quote before generating; results are saved privately and can be attached to storyboard shots.

What you provide

A description and optional images: up to 9 with H3 or Seedance 2.0, or 30 with Seedance 2.5. Compatible completed videos from your account can also be referenced.

What you get

The original playable, downloadable MP4, a poster and a separate task record.

Use Sparkles to generate individual product video clips for a launch, product page or Black Friday campaign. Start with a reference photo and a specific shot brief, inspect the result, then assemble approved clips and accurate offer text in your editing workflow.

What you provide

A product photo you may use, the feature to show, a background and one camera or object movement.

What you get

A private, downloadable MP4 clip and its task record. Final campaign editing, offer text and publishing are separate steps.

B-roll is supporting footage used alongside the main action or narration. In Sparkles, describe the missing shot, optionally add reference images, and generate a separate clip. Match its lighting and composition to your project before adding it to your final edit.

What you provide

The purpose of the insert, a scene description, optional reference images and the visual continuity to preserve.

What you get

A private MP4 supporting clip to preview, download and place in your own video edit.

Pinterest Predicts 2026 describes Neo Deco as a modern take on Art Deco, with chevrons, fan arches and chrome or brass details. Use those specific elements to explore a poster or product setting in Sparkles, then refine composition and add final text separately.

What you provide

A design purpose, a palette, one geometric motif and optional product or composition references you may use.

What you get

AI-generated still-image concepts. A moodboard or final poster layout is a separate arrangement and editing step.

Turn a portrait into a short Halloween costume reveal. First prepare the look you want, then animate it in the video studio; or use two matching outfit images in the particle transition workflow. Start with one person, one costume change and one camera move so the result is easier to inspect.

What you provide

A clear photo you may use, a costume reference or prepared costume image, and a short description of the reveal. Use the same subject and similar framing across references.

What you get

A private AI-generated MP4 to preview and download. Costume preparation produces a separate still image; a prompt is not a finished video.

An AI outfit transition changes clothing while trying to preserve the person. Sparkles offers two routes: a built-in particle outfit change in the 360° studio, or a custom scene such as a ceiling fan reveal in the video studio. Choose the route before preparing references, because the controls and camera movement differ.

What you provide

For particle change: exactly two outfit images of the same person, old look first and new look second. For custom video: a prompt and clearly assigned appearance references.

What you get

A five-second silent orbit MP4 with the particle preset, or a custom generated MP4 from the video studio. The 360° viewer can also save the currently displayed frame as PNG.

The 360° studio turns a still image into an interactive sequence of views. Use the dedicated workspace to upload and generate, or create and display the same views inside an infinite canvas. Choose Orbit Light (MiniMax H3: 768P / 2K) or Orbit Plus (Seedance 2.0: 720P / 1080P) for a silent five-second video. Particle outfit change uses exactly two ordered outfit images of the same person.

What you provide

Standard 360°: 1–9 PNG, JPEG or WebP images of the same subject, up to 16 MB each. Front, back and side views can be in any order. Particle outfit change uses exactly two ordered outfit images of the same person.

What you get

The generated private original MP4, draggable or playable, with lossless PNG export of the current original frame.

An AI infinite canvas keeps reference images, notes, generated results and a creative assistant in one zoomable workspace. Keep the original, compare versions side by side and continue from a selected image when your visual project needs several rounds of refinement. Turn an image into a draggable orbit view. Choose Orbit Light (MiniMax H3: 768P / 2K) or Orbit Plus (Seedance 2.0: 720P / 1080P) for a silent five-second video.

What you provide

Uploaded, pasted or dropped images, saved library images, creative notes and images from an existing conversation.

What you get

A private canvas of images and notes, new images connected to their sources, a PNG of the selection or whole board, and a ZIP of selected originals. You can also analyze one image and extract selected elements as separate transparent PNG assets.

A moodboard brings color, texture, composition and atmosphere together as a visual reference. Arrange your own assets on the canvas, explain your choices with notes and optionally generate supporting images to make a creative direction easier to discuss.

What you provide

Reference photos you may use, existing images, project requirements and notes on color, texture or composition.

What you get

An editable private inspiration canvas and a PNG of a selected area or the complete moodboard.

Develop a short drama as a connected script, characters, scenes and ordered shots. Preview blocking with editable 3D cameras and keyframes, generate native H3 video versions, and share a fixed workflow for others to copy into private projects. Choose H3, Seedance 2.0 or Seedance 2.5, with audio and subtitle controls.

What you provide

A story brief, character and scene details, 5/10/15-second shot timing and optional private image references.

What you get

A saved storyboard, 3D previews, private H3 video versions and reusable workflow JSON or revocable share links. Ordered previews and a private MP4 film assembled from selected video versions.

AI text to speech turns a written script into audio you can play and download. The MiMo V2.5 voice studio supports preset voices, voice design and reference-based voice cloning. For a first narration, choose a preset and start with a short English or Chinese script.

What you provide

A spoken script, a preset voice and optional instructions for emotion, pace or character delivery.

What you get

Private speech recordings with browser playback, WAV download, script reuse and record deletion.

Voice cloning uses a recording as a vocal reference when reading your new script. Choose Voice cloning in the studio, then upload or record your own voice, or a voice you have explicit permission to use, to create new English or Chinese narration.

What you provide

An authorized, clear 5–30 second voice sample, a new script and optional delivery instructions.

What you get

Private WAV speech guided by the sample, with playback, download and deletion. An exact match to the original voice is not guaranteed.

Voice design lets you describe vocal qualities in words and have that voice read a script. It is useful for exploring an original narrator or fictional character. Unlike voice cloning, it does not require a reference recording to get started.

What you provide

A required voice description and an English or Chinese script, each up to 2,000 characters.

What you get

Private WAV speech guided by your description, with playback, script reuse, download and deletion.

An outfit breakdown organizes the clothing, shoes, bags and accessories visible in a photo into a visual explanation. Upload a source image to the creative assistant and directly ask it to generate an outfit breakdown image based on visible details.

What you provide

A clear outfit photo you may use, items to include, label language, aspect ratio and requested image count.

What you get

AI-generated outfit breakdown images to download or compare on the canvas, not clothing CAD patterns or material test reports.

Turn a conversation into a downloadable report, travel guide, presentation or table. Review the outline and content with the assistant, specify the file format and ask it to export the document.

What you provide

Instructions, source material, an outline or table data, and optional supported images.

What you get

PDF, DOCX, PPTX, XLSX or Markdown files, depending on your request.

Turn a sheet of animation frames into a playable GIF. Preview the sequence, adjust the grid and export locally without signing in.

What you provide

A local sprite sheet and its frame layout.

What you get

Animated GIF, PNG atlas and JSON frame data.

Build a travel plan around dates, interests and a budget. Check linked sources, refine daily routes and export an illustrated guide.

What you provide

Destination, dates, traveller preferences and budget.

What you get

A researched itinerary, source links and optional illustrated documents.