🏷 Crisp Upscale is 20% off — 2 credits instead of 2.5Try it•🏷 Creative Upscale is 20% off — 50 credits instead of 62.5Try it•🏷 Clarity Upscaler is 20% off — 6 credits a megapixel instead of 7.5Try it•🏷 Qwen Edit 2511 is 20% off — 6 credits instead of 7.5Try it•🏷 FLUX Erase is 20% off — 10 credits instead of 12.5Try it•🏷 Seedream 4.5 Edit is 20% off — 8 credits instead of 10Try it•🏷 Seedream 5 Flash Edit is 20% off — 6 credits instead of 7.5Try it•🏷 Nano Banana 2 Edit is 20% off — 16 credits instead of 20Try it•🏷 Nano Banana 2.1 Edit is 20% off — 10 credits instead of 12.5Try it•🏷 FLUX.2 Klein 9B Edit is 21% off — 5 credits instead of 6.3Try it•🏷 Ideogram Character is 20% off — 30 credits instead of 37.5Try it•🏷 GPT Image 2 Edit is 20% off — 43 credits instead of 53.8Try it•🏷 GPT Image 2.5 Flare Edit is 20% off — 11 credits instead of 13.8Try it•🏷 GPT Image 2.5 Sunburst Edit is 20% off — 11 credits instead of 13.8Try it•🏷 Meta Muse Edit is 20% off — 2 credits instead of 2.5Try it•🏷 Grok Imagine Edit is 21% off — 5 credits instead of 6.3Try it•🏷 Bria Expand is 20% off — 8 credits instead of 10Try it•🏷 Ideogram Reframe is 20% off — 12 credits instead of 15Try it•🏷 Topaz Video Upscale is 20% off — 4 credits a second instead of 5Try it•🏷 FLUX Video Upscale is 20% off — 28 credits a second instead of 35Try it•🏷 Grok Imagine Extend is 20% off — 20 credits a second instead of 25Try it•🏷 Lucy Edit Pro is 20% off — 30 credits a second instead of 37.5Try it•🏷 Kling O3 4K Edit is 20% off — 84 credits a second instead of 105Try it•🏷 Luma Modify is 20% off — 70 credits a second instead of 87.5Try it•✨ New: Nano Banana 2.1Try it•✨ New: Grok Video 1.5 LiteTry it•Credits never expire — whatever you buy rolls over foreverSee pricing•

Generating images

Make one to four pictures from a prompt, in the shape you need.

The Image lane makes new pictures from words. Pick a model, describe the picture, choose its shape, and press Generate image. Every result is saved for you.

Where
Sidebar → Images (the Studio’s Image lane)
Cost
From 1 credits a picture, shown on the button before you run
Saved to
Your Library, automatically

Make an image

  1. 1
    Open Images in the sidebar. The Studio opens on the Image lane with Auto picked.
  2. 2
    Keep Auto, or open the Model list and pick one. See Choosing a model.
  3. 3
    Describe the picture in Prompt: subject, setting, style and light.
  4. 4
    Set Images to 1–4 with − and +.
  5. 5
    Pick an Orientation. 16:9 Widescreen is picked at first.
  6. 6
    Press Generate image. The price is on the button.
The Image lane with Seedream 4 picked, a candle prompt typed, Images set to 2, Widescreen orientation, and the Generate image button showing its price.
NoteOn Auto, the button reads cost varies. Auto picks the model when you run: Recraft V3 for prompts about logos, posters, signs or text, and Seedream 4 for everything else. You pay that model’s price, and the result names it.

Batches

Each run makes 1 to 4 pictures, and each picture costs the model’s price. Four takes on one prompt is the cheapest way to find a keeper.

Recraft V3, Recraft V4.1 and FLUX 2 Pro make one picture per run. Ask them for more and the extra credits come straight back.

Orientation

There are ten shapes: Square (1:1), Widescreen (16:9), Story (9:16), Social post (4:5), Portrait (3:4), Portrait tall (2:3), Classic (4:3), Standard (3:2), and the Horizontal (2:1) and Vertical (1:2) banners. Pick the shape before you run — it’s part of the request, not a crop.

Some models only make certain shapes. They round your pick to the nearest shape they support, so a 2:1 banner may come back 16:9.

Steer the result

These sit with the prompt box, on the models that support them.

Avoid (negative prompt, optional)
List what to keep out: “blurry, extra fingers, text, watermark”. Up to 500 characters. Only on models that take it, such as Ideogram 3 and Wan 2.7.
🎨 Style
Opens a gallery of your own styles and the built-in ones. Pick one and “in the style of @…” is added to your prompt. A new pick replaces the last one.
@ entities
Type @ to add a saved character, prop, place or style. Image-lane models can’t take reference pictures, so each one sends its written description. One with no description is stopped before you’re charged. See Entities.
Show starter prompts
Prompts known to work on the chosen model. Click one to fill the box. Shown only on models that have them.

Results

Results appear in the panel on the right. One picture fills the panel; a batch sits side by side. Click any picture to open it full size in a new tab.

Under the result, a row shows the model, how long it took and what it cost. ✓ Saved to your Library · Open full size ↗ confirms the save. A Recent work strip under the Studio shows your latest creations on this device.

Animate a result

Under a picture, 🎬 Animate this with Kling 2.5 Turbo Pro · −88 cr turns it into a 5-second video. Under a batch it reads 🎬 Animate the first with … and uses the first picture.

Heads upOne click starts the paid video right away. It uses the words in your prompt box as the motion prompt. To choose the model, length and motion yourself, use the Video lane — see Animating an image.

Several runs at once

You don’t have to wait. Press the button again and the next run starts while the first one works. Each run gets a card with a timer, and the newest finished result shows in the panel.

Four slower models — Seedream 4.5, GPT Image 2, Wan 2.7 and Grok Imagine 2 — wait in line the way video does. They keep going if you close the page and land in your Library. If one is still running when you come back, its card returns. While one is waiting in line, its card shows Cancel · refund.

While runs are going, two buttons sit under the cards. 🔔 Tell me when it's ready plays a chime and shows a desktop notice when a run finishes while you’re on another tab. 📧 Email me when it's ready emails you if you’ve left the page when one of the slower runs finishes. Both stay on until you switch them off.

More in Creating Images, Video & Audio

← Back to the Help Center