Seedream 5 pro
ByteDance’s flagship Seedream-5-pro text-to-image and image editing model that turns prompts or up to 10 reference images into sharp 1K/2K visuals.

Price per run
from$0.2010 credits
- ✓ No subscription
- ✓ Pay per generation
- ✓ Credits valid 12 months
Pricing
What Seedream 5 pro costs
You pay per generation. The app shows the exact price as you change the settings, before you click Generate.
One run costs $0.20, depending on the options you pick.
Credit packs from $4.99 for 200 credits. No monthly plan. See all packs
How to Use the App
Here’s what you get when you open the app: a short form, one run button, your results — no nodes, no setup.
Seedream 5 pro
App previewFill in the form
Prompt
RequiredType your prompt…
Aspect Ratio
Match Input Image
Image Input
Add images or files
Output Format
png
Size
2K
≈ 10 credits / run
Get your result

Real output generated with this app
What This App Does
Seedream-5-pro is ByteDance’s premium text-to-image and image-to-image model for creating high-fidelity visuals with strong prompt adherence and consistent style control. It generates detailed 1K (~2MP) or 2K (~4MP) images from text alone or by guiding generation with up to 10 reference images for single or multi-reference workflows.
Inputs and controls
prompt (required) — Up to 4000 characters; for best results, keep prompts under ~600 English words.
image_input (optional) — 1–10 reference images for image-to-image or multi-reference guidance.
size — Choose 1K or 2K resolution.
aspect_ratio — Fixed ratios (1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9) or match_input_image to align with a provided image’s aspect.
output_format — png or jpeg.
Output: - Returns an array of image URLs (URIs) ready for download or downstream processing.
Ideal for ad creatives, product shots, key art, moodboards, thumbnails, and brand imagery where sharp detail, controllable style, and multi-reference consistency matter. Combine descriptive prompts with reference images to capture subject likeness, composition, palette, and texture.
Best practices
Be specific about subject, composition, style, lighting, materials, mood, and camera/lens cues.
When using references, indicate which elements to prioritize (e.g., “use reference 1 for pose, reference 2 for color palette”).
Use aspect_ratio = match_input_image to preserve layout from a reference.
Prefer 2K for cropping or print-quality detail; use PNG for crisp edges or transparency and JPEG for lighter file sizes.
Keep prompts concise and focused; iterate with small, clear adjustments.
Other Image models
Compare before you generate
Remix this appFor builders: open the workflow behind it to swap the model, chain steps, run batches or call it from the API.
Under the Hood
Want more control?
This app is powered by a fully editable AI-Flow workflow. Change the model, prompts, layout, resolution — or connect it to other steps.
Prompt
Create an artistic hero illustration for an AI image model called “Seedream 5 Pro”. Visual concept: a delicate seed resting in a surreal painted dreamscape, slowly blooming into flowing brushstrokes, soft petals, clouds of pigment, ink washes, golden dust, ...
Image Input
Optional references or files.
Seedream-5-pro

How to Use This Template
Step 1: Enter your text in 'Prompt' Node
Fill the 'Prompt' node with the required text.
Create an artistic hero illustration for an AI image model called “Seedream 5 Pro”. Visual concept: a delicate seed resting in a surreal painted dreamscape, slowly blooming into flowing brushstrokes, soft petals, clouds of pigment, ink washes, golden dust, and abstract shapes of imagination. The image should feel poetic, refined, calm, and premium, like a gallery artwork made for a creative app. Style: painterly, elegant, expressive, contemporary art direction, soft natural textures, watercolor and oil-paint influence, subtle paper grain, warm ivory, muted sage, dusty rose, soft lavender, deep indigo accents, gentle golden highlights, atmospheric lighting. Typography: include the exact text “Seedream 5 Pro” as the main title, clean and readable, elegant serif or refined minimalist lettering, naturally placed within the artwork. No spelling mistakes, no extra text. Composition: centered app feature card or banner, graceful negative space, balanced and premium, suitable for a creative AI tool launch screen. Artistic, poetic, painterly, sophisticated, high-resolution, refined composition.
Step 2: Upload your files
In the 'Image Input' node, upload the files you want to use in the workflow.
Step 3: Run the Flow
Click the 'Run' button to execute the flow and get the final output.

Frequently Asked Questions
Do I need a subscription to use Seedream 5 pro?
No. Buy a credit pack once, generate, and come back whenever you want. Purchased credits stay valid 12 months, and every new purchase extends them.
What is Seedream-5-pro?
A ByteDance flagship model for text-to-image and image-to-image editing. It generates sharp 1K or 2K images from a prompt and optionally up to 10 reference images.
How many reference images can I upload?
You can provide 1–10 reference images for single or multi-reference guidance to influence composition, style, or subject likeness.
Which resolutions and aspect ratios are supported?
Resolutions: 1K (~2MP) and 2K (~4MP). Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9, or use match_input_image to align with your reference.
What output formats are available?
PNG and JPEG. Choose PNG for crisp edges or transparency needs and JPEG for smaller file sizes.
How long can my prompt be?
Up to 4000 characters. For best results and clearer output, keep prompts under ~600 English words.
Does it preserve the composition of my input image?
Use aspect_ratio = match_input_image and give clear instructions to help preserve layout and key elements from your reference.
Is it suitable for both photorealistic and stylized outputs?
Yes. You can steer toward photorealism or stylized art by specifying style cues, materials, lighting, and camera settings in the prompt.
What does the model return?
An array of image URLs (URIs) that you can download or pass to downstream tools and workflows.
Can I combine text prompts with reference images?
Yes. Provide a descriptive prompt along with 1–10 references to blend textual intent with visual guidance.
When should I choose 1K vs 2K?
Use 1K for quick previews or web visuals and 2K for higher detail, cropping flexibility, or print-oriented assets.
Any tips for better prompt quality?
Include subject, setting, composition, style, lighting, and what to avoid. If using multiple references, note which image controls pose, color, or texture.
How do I know what a generation will cost?
The app shows the exact price on the Generate button and updates it as you change the settings, before anything is billed.
Is there a free trial available?
Yes, AI-FLOW offers a free trial to get you started. After that, you can purchase credits as needed—no subscription or long-term commitment required.