Try Seedream 4.5 Text to Image with real landscape, food, sci-fi, and Chinese-aesthetic examples, eight ratios, 2K/4K output, and API code.
Provider: ByteDance
Category: image generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
Try Seedream 4.5 Text to Image with real landscape, food, sci-fi, and Chinese-aesthetic examples, eight ratios, 2K/4K output, and API code.
Pricing
Standard Usage
Ready for generation
Configure your parameters and click "Run" to see the output here.
Browse real API results across different aspect ratios, complete prompts, and visual detail.
Choose an adjacent model by task, output tier, and reference-image needs.
Multi-reference editing
Use the companion route for up to fourteen references and controlled image edits.
Newer low-cost generation
Compare a newer flat-price route with 2K/4K output and eight ratios.
Campaign-grade generation
Use the Pro route for demanding text, material, and final campaign composition.
Try Seedream 4.5 Text to Image with real landscape, food, sci-fi, and Chinese-aesthetic examples, eight ratios, 2K/4K output, and API code.
The Playground and API use the same model ID: seedream-4.5/text-to-image. This endpoint accepts text prompts only; reference-image editing uses the separate Image-to-Image route.
These specifications reflect the current Seedream 4.5 Text to Image request contract.
Final cost depends on the output tier and input add-ons. Check the live page price and task record for the final charge.
Choose the destination and aspect ratio before composing subject, scene, material, light, and text.
Copy a minimal request below. See Docs for parameters, callbacks, task retrieval, and errors.
POST /v1/tasksseedream-4.5/text-to-imagecurl -X POST https://api.hiapi.ai/v1/tasks \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-4.5/text-to-image",
"input": {
"prompt": "A cinematic product campaign with sharp text",
"aspect_ratio": "1:1",
"resolution": "2K"
}
}'The create request immediately returns a taskId; image generation continues asynchronously.
Chinese-aesthetic scenes, food photography, sci-fi, landscapes, and general creation that needs 2K or 4K output.
Both resolutions currently use the same per-image tier. See the live page price for the current amount.
The current contract requires explicit aspect_ratio and resolution so output sizing does not rely on an implicit default.
Not on this route. Use seedream-4.5/image-to-image.
Four to 3,000 characters, in Chinese or English.
Start with the subject, environment, and visual goal, then add material, light, camera, and exact text.
Draft
2K
Final
4K
Choose one of eight ratios and render at 2K or 4K.
Confirm the result in Playground, then reuse the same prompt and model ID in an asynchronous task.