Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
Use Seedream in WorkBuddy.
Seedream is Bytedance's image generation model with strong typography rendering and up to 4K output. WorkBuddy calls it through the runapi MCP server — the same server and RUNAPI_API_KEY that cover chat expose Seedream as a callable tool in the workbench, with no extra provider accounts.
Generate a 4K product hero image using Seedream through the runapi MCP server.
Requirements:
- Call the image generation tool exposed by the runapi MCP server.
- Set model to "seedream-4.5-text-to-image".
- Prompt: "A premium coffee bag on a marble countertop, warm morning light, bold serif text FRESH ROAST, 4K product photography."
- Wait for the task to complete and return the generated image URL.
{
"mcp_servers": {
"runapi": {
"url": "https://runapi.ai/mcp",
"transport": "streamable_http",
"headers": {
"Authorization": "Bearer $RUNAPI_API_KEY"
}
}
}
}
{
"task_id": "tsk_abc123",
"status": "completed",
"model": "seedream-4.5-text-to-image",
"output": {
"image_url": "https://media.runapi.ai/outputs/tsk_abc123.png"
}
}
Use Seedream in WorkBuddy in three steps
Add the RunAPI MCP server
Register an MCP server named runapi in WorkBuddy pointing at https://runapi.ai/mcp over streamable HTTP, with the Authorization header reading your key from RUNAPI_API_KEY. If RunAPI is already connected in WorkBuddy for chat, you are done — the same server exposes Seedream.
url: https://runapi.ai/mcp
Prompt the workbench agent
Ask WorkBuddy to generate an image with model seedream-4.5-text-to-image and a text prompt describing the scene, including any typography you want baked into the image. Switch the slug to seedream-5-lite-text-to-image when you want faster, cheaper drafts.
Generate a 4K hero image with Seedream
Get the result
WorkBuddy calls the RunAPI MCP tool, which runs the generation as an async task and polls the status for you. When the status changes to completed, the agent reports the generated image URL back in the workbench.
task_id: tsk_abc123
Seedream API parameters
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. seedream-4.5-text-to-image, seedream-4.5-edit, seedream-5-lite-text-to-image. |
prompt |
string |
Text description of the desired image. Include any text you want rendered. |
size |
string |
Optional. Output dimensions. Supports up to 4K. |
image_url |
string |
Source image for editing mode with seedream-4.5-edit. |
What is Seedream on WorkBuddy?
Seedream is ByteDance's image model that users describe as offering "unmatched value" with 4K-quality output and 94% text accuracy out of the box. It holds onto structure in complex prompts — multiple objects, specific spatial relationships, detailed typography — without losing coherence. WorkBuddy reaches it through the runapi MCP server, using the same RUNAPI_API_KEY that covers every other model in the catalog.
Seedream use cases
E-commerce product catalogs
Generate product lifestyle shots with accurate labels and pricing text baked into the image, ready for catalog pages without post-production text overlays.
Typography-heavy poster and event design
Create event posters, signage, and billboards where the text content is specified in the prompt and rendered at 94% accuracy or better.
Batch generation for brand campaigns
Ask the workbench agent to generate a consistent character or product series across dozens of images, maintaining the same brand ambassador appearance and house style throughout.
Seedream + WorkBuddy questions
Add RunAPI as an MCP server named runapi pointing at https://runapi.ai/mcp with your RUNAPI_API_KEY, then prompt the workbench agent to generate an image with model seedream-4.5-text-to-image. The agent calls the RunAPI MCP tool and returns the finished image URL.
No. The same RUNAPI_API_KEY behind the runapi MCP server also calls Seedream and every other image model in the RunAPI catalog. One key, one billing account.
Generation runs as an async task that returns a task_id. The RunAPI MCP server handles status polling, so the WorkBuddy agent simply reports the image URL when the status is completed. Failed generations are not charged.
Yes. Describe the character in detail across prompts and Seedream maintains facial features, body proportions, and clothing style across a batch of images, making it suitable for brand ambassador series or product model sequences.
Seedream 4.5 is the full model with 4K output and the highest fidelity. Seedream 5 Lite is a faster, cheaper variant optimized for speed at standard resolution. Both are exposed through the same runapi MCP server — set the model slug to seedream-5-lite-text-to-image for faster generation or seedream-4.5-text-to-image for maximum quality.
WorkBuddy general setup
Not configured yet? Start with the RunAPI MCP setup guide for WorkBuddy.
WorkBuddy setup guide →Try Seedream in WorkBuddy today.
Get a free RunAPI key, add the MCP server to WorkBuddy, and start generating 4K images with Seedream.