Edit with Seedream 5.0 Lite Image to Image using up to 14 references, real recolor, text replacement, and composite examples, 2K or 4K output, and API code.
Provider: ByteDance
Category: image generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
Edit with Seedream 5.0 Lite Image to Image using up to 14 references, real recolor, text replacement, and composite examples, 2K or 4K output, and API code.
Pricing
Standard Usage
Ready for generation
Configure your parameters and click "Run" to see the output here.
Each case separates references, the edit instruction, and the complete result, with image zoom and prompt copy.
1 reference image(s) / 2496 × 1664
The mug becomes glossy cobalt while steam, desk, notebook, pen, plant, lighting, and camera stay fixed.
Change the matte white ceramic mug into a deep cobalt blue glazed mug with a glossy reflective finish, keep the steam, the oak desk, the open notebook, the fountain pen, the succulent, the lighting and the camera angle exactly unchanged, photorealistic
Product reference
Scene reference
Result2 reference image(s) / 2496 × 1664
The backpack comes from the first reference while the granite rock, forest, mountains, and golden-hour light come from the second.
Take the leather backpack from the first image and place it on the flat granite boulder in the campsite scene from the second image, leaning naturally at a slight angle, relit to match the warm golden-hour sunlight with a soft shadow falling across the rock, keep the stone fire ring, pine forest and mountain peaks unchanged, photorealistic composite
1 reference image(s) / 2496 × 1664
Only the sign copy changes while its gold serif style, wood, brick, window light, plants, and weather remain.
Replace the text on the wooden sign above the door so it reads 'BAKERY CORNER' in the same gold serif lettering style and size, keep the sign shape and wood texture, the brick facade, the glowing window, the olive trees and the overcast lighting exactly unchanged, photorealistic
Choose an adjacent model by task, output tier, and reference-image needs.
Higher-fidelity editing
Use the Pro route for final campaign assets and demanding preservation work.
2K or 4K multi-reference editing
Compare up to 14 references with explicit 2K and 4K output tiers.
Single-reference commercial editing
A fast single-reference route for text replacement, cleanup, and product restaging.
Edit with Seedream 5.0 Lite Image to Image using up to 14 references, real recolor, text replacement, and composite examples, 2K or 4K output, and API code.
The Playground and API use the same model ID: seedream-5.0-lite/image-to-image. Reference images provide subject, product, scene, or style facts, while the prompt assigns each role and limits the edit.
These specifications reflect the current Seedream 5.0 Lite Image 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.
References provide visual facts; the prompt assigns their roles and limits the edit.
Copy a minimal request below. See Docs for parameters, callbacks, task retrieval, and errors.
POST /v1/tasksseedream-5.0-lite/image-to-imagecurl -X POST https://api.hiapi.ai/v1/tasks \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-5.0-lite/image-to-image",
"input": {
"prompt": "Change the product color and preserve its structure",
"image_urls": [
"https://example.com/reference.jpg"
],
"aspect_ratio": "1:1",
"resolution": "2K"
}
}'The create request immediately returns a taskId; image generation continues asynchronously.
It accepts 1 to 14 JPEG, PNG, or WebP images under 10MB each. Use one for focused edits or multiple references for subject and scene composites.
No. Pricing is fixed per output image, independent of reference count, 2K or 4K tier, and aspect ratio. See the live page price for the current amount.
Describe both the target change and the composition, text, material, lighting, and positions that must remain unchanged.
Yes. State the old and new copy and ask it to preserve the original type style, size, position, and glow or print treatment.
Pass 1 to 14 public image URLs in input.image_urls when posting to /v1/tasks, together with the prompt, ratio, and 2K or 4K resolution.
Choose 1 to 14 publicly accessible images without redundant or conflicting roles.
Describe the requested edit and the subject, text, composition, lighting, and positions that must remain.
Check the reference relationship in Playground, then create asynchronous tasks with the same model ID.