New — access 450+ AI models through one unified API.Start building free

seedream-v5.0-lite/edit

Schema
LLMs

Seedream 5.0 Lite Edit by is a state-of-the-art image editing model preserving facial features, lighting, and color tones from reference images. Features high-fidelity editing with professional quality, superior prompt adherence, and up to 4K resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-image$0.0400/ run

Prompt

Enhancer
0/2000

Image

PreviewJSON

Your result will appear here

Upload an image, write a prompt and hit Generate.

Examples

Keep the model's pose and the flowing shape of the liquid clothing unchanged. Change the clothing material from silver metal to completely transparent clear water (or glass). Through the liquid water flow, the details of the model's skin can be seen. The light and shadow change from reflection to refraction. Change the background to a night city.

Keep the model's pose and the flowing shape of the liquid clothing unchanged. Change the clothing material from silver metal to completely transparent clear water (or glass). Through the liquid water flow, the details of the model's skin can be seen. The light and shadow change from reflection to refraction. Change the background to a night city.

Related models

seedream-v5.0-protext-to-image
seedream-v5.0-pro

Seedream V5.0 Pro generates high-quality images from text prompts with aspect ratio selection, strong prompt following, and 1K / 2K output tiers. It supports multi-language text rendering, layer separation for design workflows, and professional-grade image quality. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedream$0.0450
seedream-v5.0-pro / editimage-to-image
seedream-v5.0-pro / edit

Seedream V5.0 Pro Edit edits and generates images from single-image or multi-reference inputs, supporting up to 10 reference images, aspect ratio selection, and 1K / 2K output tiers. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedream$0.0450
seedream-v5.0-litetext-to-image
seedream-v5.0-lite

Seedream 5.0 Lite by is a state-of-the-art text-to-image model with enhanced typography, clear text rendering for posters and brand visuals, superior prompt adherence, and up to 4K resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Seedream$0.0400
seedream-v4.5 / editimage-to-image
seedream-v4.5 / edit

Seedream 4.5 Edit preserves facial features, lighting, and color tone from reference images, delivering professional, high-fidelity edits up to 4K with strong prompt adherence. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedream$0.0400
seedream-v4.5text-to-image
seedream-v4.5

Seedream 4.5 is a next-gen text-to-image model optimized for typography—crisper text rendering, stronger prompt adherence, and up to 4K output for posters and brand visuals. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedream$0.0400

Seedream V5.0 Lite Edit

Seedream 5.0 Lite Edit by is a state-of-the-art image editing model preserving facial features, lighting, and color tones from reference images. Features high-fidelity editing with professional quality, superior prompt adherence, and up to 4K resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Key Features

  • Transform existing images using text prompts while preserving key structural elements.
  • Style transfer — apply artistic styles, color grading, or visual themes to source images.
  • Intelligent inpainting and editing — modify specific regions while keeping the rest intact.
  • Strength control — fine-tune how much the output deviates from the source image.
  • Fast inference with consistent, high-quality results.
  • Supports various input formats: JPEG, PNG, WebP.

Parameters

ParameterRequiredDescription
promptYesText description of the desired transformation.
imagesYesSource image URL(s) to transform.
aspect_ratioNoOutput aspect ratio (default: auto-detected from input).
resolutionNoOutput resolution tier (default varies by model).

How to Use

  1. Upload or provide a URL for your source image.
  2. Write a prompt describing the desired transformation or style.
  3. Adjust parameters to control how much the output differs from the original.
  4. Generate and download your transformed image.

Code Examples

import os
import requests

response = requests.post(
    "https://aircube.ai/api/v3/seedream-v5.0-lite/edit",
    headers={
        "Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
    "prompt": "Transform into a watercolor painting style",
    "images": [
        "https://example.com/input.jpg"
    ]
},
    timeout=300,
)
data = response.json()

if data["success"]:
    print("ID:", data["data"]["id"], "Status:", data["data"]["status"])
else:
    print("Error:", data["error"]["message"])

Pricing

ResolutionDurationCost
2kper image$0.04
3kper image$0.04

Billing rules

  • Per image: 2k: $0.04, 3k: $0.04.
  • Failed generations are not charged.

Best Use Cases

  • Style transfer — convert photos into paintings, sketches or other artistic styles.
  • Product visualization — change colors, materials or environments of product photos.
  • Photo enhancement — improve lighting, add atmospheric effects, or change seasons.
  • Brand asset adaptation — transform templates to match different campaigns or audiences.

Pro Tips

  • Use lower strength values to preserve more of the original structure.
  • Higher strength gives the model more creative freedom for dramatic transformations.
  • Upload high-resolution source images for the best output quality.
  • Combine detailed prompts with moderate strength for controlled style changes.

Notes

  • Input images should be under 10 MB.
  • Supported formats: JPEG, PNG, WebP.
  • Aspect ratio of the output matches the input image by default.

Seedream V5.0 Lite Edit — Frequently asked questions