Images
seedream-5-pro
Edit with references, or place them by hand.
<!-- Generated by apps/docs/scripts/gen-tools.mjs. Do not edit here: the words live in apps/web/src/lib/tools/seedream.tool.json (agent, hint) and packages/shared/src/tools/setting-hints.ts. --> On the rail as **seedream-5-pro**. ## When to use it Editing an image against up to nine references with one instruction, or dropping a base image and dragging each reference to where it belongs. ## When to reach for something else It always starts from a source or base image, so building a picture from nothing is a different tool's job. References cap at nine beside that base, and in Compose the placement is dragged by hand, not described in words. ## How to use it 1. Drop one or more pictures onto the card's **Images** slot. 2. Write what you want in **Prompt**. 3. Pick a model in the pill at the top of the card, or keep **Edit**. 4. Press **Run**. ## On the card | Control | What it does | Choices | | - | - | - | | Images | The pictures the tool works from. Drop them from the board or your computer, then refer to each one by number in the prompt. | Several pictures | | Prompt | What you want, in your own words. The card sends it with your inputs. | Your words | | Run | Starts the run. The number on it is what this run costs in credits, worked out before you press. | | | ×1 | Runs the card several times in a row with the same settings. | 1 to 99 | ## Models The pill at the top of the card picks the model. **Edit** is the one a new card starts on. | Model | Good for | | - | - | | [Edit](#edit) | Instruction-led edits across up to ten reference images, and the photographic choice where it sits beside a stylising model: compositing a subject into a scene, recomposing one frame per platform, fusing objects. | | [Compose](#compose) | Layout by hand: drop a base image, drag each reference to where it should sit, and the model composes them in place using its spatial-annotation strength; the prompt is optional direction, not the layout. | ### Edit **Not the one for:** Output tops out at the 2K preset and there is no mask, quality ladder or seed here, so it is the wrong pick for a 4K deliverable or a strictly masked local fix. Behind the settings button: | Setting | What it does | Choices | | - | - | - | | Size | Output resolution. Auto 2K is the default quality tier; Auto 1K is cheaper. | Auto 2K, Auto 1K, Square large, Square small, Horizontal 16:9, Vertical 9:16, Horizontal 4:3, Vertical 3:4 | ### Compose **Not the one for:** It needs a base image with references placed on it, so a single picture with a written change, or a blend with no fixed positions, is the Edit side of the same card. Behind the settings button: | Setting | What it does | Choices | | - | - | - | | Size | Output resolution. Auto 2K is the default quality tier; Auto 1K is cheaper. | Auto 2K, Auto 1K, Square large, Square small, Horizontal 16:9, Vertical 9:16, Horizontal 4:3, Vertical 3:4 |On the rail as seedream-5-pro.
When to use it
Section titled “When to use it”Editing an image against up to nine references with one instruction, or dropping a base image and dragging each reference to where it belongs.
When to reach for something else
Section titled “When to reach for something else”It always starts from a source or base image, so building a picture from nothing is a different tool’s job. References cap at nine beside that base, and in Compose the placement is dragged by hand, not described in words.
How to use it
Section titled “How to use it”- Drop one or more pictures onto the card’s Images slot.
- Write what you want in Prompt.
- Pick a model in the pill at the top of the card, or keep Edit.
- Press Run.
On the card
Section titled “On the card”| Control | What it does | Choices |
|---|---|---|
| Images | The pictures the tool works from. Drop them from the board or your computer, then refer to each one by number in the prompt. | Several pictures |
| Prompt | What you want, in your own words. The card sends it with your inputs. | Your words |
| Run | Starts the run. The number on it is what this run costs in credits, worked out before you press. | |
| ×1 | Runs the card several times in a row with the same settings. | 1 to 99 |
Models
Section titled “Models”The pill at the top of the card picks the model. Edit is the one a new card starts on.
| Model | Good for |
|---|---|
| Edit | Instruction-led edits across up to ten reference images, and the photographic choice where it sits beside a stylising model: compositing a subject into a scene, recomposing one frame per platform, fusing objects. |
| Compose | Layout by hand: drop a base image, drag each reference to where it should sit, and the model composes them in place using its spatial-annotation strength; the prompt is optional direction, not the layout. |
Not the one for: Output tops out at the 2K preset and there is no mask, quality ladder or seed here, so it is the wrong pick for a 4K deliverable or a strictly masked local fix.
Behind the settings button:
| Setting | What it does | Choices |
|---|---|---|
| Size | Output resolution. Auto 2K is the default quality tier; Auto 1K is cheaper. | Auto 2K, Auto 1K, Square large, Square small, Horizontal 16:9, Vertical 9:16, Horizontal 4:3, Vertical 3:4 |
Compose
Section titled “Compose”Not the one for: It needs a base image with references placed on it, so a single picture with a written change, or a blend with no fixed positions, is the Edit side of the same card.
Behind the settings button:
| Setting | What it does | Choices |
|---|---|---|
| Size | Output resolution. Auto 2K is the default quality tier; Auto 1K is cheaper. | Auto 2K, Auto 1K, Square large, Square small, Horizontal 16:9, Vertical 9:16, Horizontal 4:3, Vertical 3:4 |