Seedream 5.5 Uncensored

About

Seedream 5.5 Uncensored is ByteDance Seed's Seedream 5.5, the newest Seedream image model, on a more permissive content policy, served through BytePlus ModelArk. Its Sogni model ID is seedream-5-5-uncensored. In Sogni Create, Seedream Uncensored opens to Seedream 5.5, and Seedream 5.0 Pro Uncensored stays available as the other version.

It creates an image from a prompt, or edits and combines up to 10 reference images in one request. Sizes run from about 0.9 megapixels up to the 2K tier, about 4.6 megapixels, such as 2048 × 2048, 2816 × 1584 for 16:9 and 3136 × 1344 for 21:9.

It can give an image a transparent background, from a prompt alone or from your references, saved as PNG or WebP. Layer extraction splits one image into a base image plus up to 99 transparent PNG layers. Each layer is named and described, with its position on the base, and you can download one layer or all of them. With text recognition on, the model reads back layers it recognizes as plain text, with their font, color and style.

In Sogni Create, Point or box edit lets you click a point or draw a box on one reference image and describe the change, as with Seedream 5.0 Pro. Edits can build on each other: in a three-round test, a portrait got a green sweater, then gold hoop earrings, then a snowy street outside the window, and her face stayed the same throughout.

It is the opt-in version for creators 18 or older making lawful mature-theme work. It appears in Sogni only after the Sensitive Content Filter is turned off, and the first render asks for the same one-time likeness and consent agreement as Seedream 5.0 Pro Uncensored and the Seedance models. Sogni's Terms of Use and the model provider's terms still apply.

Prompting tips

Write a direct brief, and give every reference image a job.

• References — Refer to reference images as Image 1, Image 2, and so on, in the order you attach them, and say what each one is for: the object, the setting, or the lighting.
• Text in the image — Put every word that must appear in quotes, and say where it goes.
• Transparent backgrounds — Describe the subject on its own, for example “isolated with nothing behind it”, and choose PNG or WebP.
• Layers — Leave the prompt empty to split every major element, or name the parts you want on their own layers.
• Mature themes — State wardrobe, framing, and action directly instead of hinting. Every depicted person must be 18 or older, and the request must stay lawful under Sogni's Terms of Use.

Pricing

Seedream 5.5 Uncensored is a pay-as-you-go Premium Spark vendor model. Every render uses Premium Spark (bought or awarded, never Free Spark), including for Sogni Unlimited members. Unlimited saves 5%; Unlimited Pro saves 10%.

Each image costs 6 Spark ($0.03) up to about 2.6 megapixels, which covers every 1K and 1.5K size, and 10.5 Spark ($0.0525) above that, up to about 4.6 megapixels. Each reference image adds 2.4 Spark ($0.012).

Layer extraction costs the same per image for the base and each layer it returns, plus 2.4 Spark ($0.012) for the source image. The quote shows the most it can cost for the number of images you allow, and you pay for what comes back.

Seedream 5.5 Uncensored runs on BytePlus and is not covered by Unlimited fair use. Unlimited saves 5% and Unlimited Pro saves 10% on these rates.

API

One Sogni API key reaches every model in the catalog — call Seedream 5.5 Uncensored with the exact model id.

import { SogniClient } from '@sogni-ai/sogni-client';

const client = await SogniClient.createInstance({
  appId: crypto.randomUUID(),
  apiKey: process.env.SOGNI_API_KEY,
  network: 'fast',
});

const project = await client.projects.create({
  type: 'image',
  modelId: 'seedream-5-5-uncensored',
  positivePrompt: 'A hand-painted watercolor hot-air balloon with red and cream stripes, isolated with nothing behind it',
  numberOfMedia: 1,
  width: 1536,
  height: 1536,
  seedreamBackground: 'transparent', // PNG with a transparent background
  tokenType: 'spark',
});

const [url] = await project.waitForCompletion();
console.log(url);

import asyncio, os
from sogni_client import SogniClient

async def main():
    async with await SogniClient.create(
        api_key=os.environ["SOGNI_API_KEY"],
        app_id="seedream-example",
    ) as sogni:
        project = await sogni.projects.create(
            type="image",
            model_id="seedream-5-5-uncensored",
            positive_prompt="A hand-painted watercolor hot-air balloon with red and cream stripes, isolated with nothing behind it",
            number_of_media=1,
            width=1536,
            height=1536,
            seedream_background="transparent",  # PNG with a transparent background
            token_type="spark",
        )
        for url in await project.wait_for_completion():
            print(url)

asyncio.run(main())

Use the JavaScript or Python SDK with the model id seedream-5-5-uncensored. The examples make a transparent PNG; leave out seedreamBackground for an ordinary image, or split one with seedreamLayerDecomposition. Options and limits are in the Seedream 5.5 Uncensored guide. Full reference at docs.sogni.ai.