# Seedream 5.5 comes to CapCut: 100 chained edits and transparent backgrounds

> ByteDance brings Seedream 5.5 to CapCut and Dreamina with 100-round editing, transparent backgrounds and better text. Benchmarks, caveats and access.


Published: 2026-11-09. Original source: [ByteDance Seed · Introducing Seedream 5.5](https://seed.bytedance.com/en/blog/more-realistic-images-more-stable-editing-across-100-rounds-introducing-seedream-5-5).

![Five Seedream 5.5 sample images: a mother and daughter on a steppe, a couple dining in a restaurant, a cat beside bottles in a bar, a fisherman mending a net and a subway platform with an illuminated sign.](/news/seedream55/official-cover.jpg)

Images generated with Seedream 5.5, published in the [ByteDance Seed announcement](https://seed.bytedance.com/en/blog/more-realistic-images-more-stable-editing-across-100-rounds-introducing-seedream-5-5). November 9, 2026; only resized for the web.

**ByteDance has released Seedream 5.5**, the new version of its model for creating and editing images. The Seed team [introduced it on November 9](https://seed.bytedance.com/en/blog/more-realistic-images-more-stable-editing-across-100-rounds-introducing-seedream-5-5) and is bringing it to **CapCut** and **Dreamina**; it also announced it for BytePlus, its platform for businesses. In CapCut it has been available in supported regions since that day, with the US coming soon, according to the app. [CapCut’s announcement](https://x.com/capcutapp/status/2119746849917878279).

The changes target everyday image work: editing the same image many times without breaking what you didn’t touch, creating assets with transparent backgrounds and getting clearer small text. The figures in this story come from ByteDance’s own evaluations; further down you’ll see which models it was measured against and what was left out.

## 100 chained edits

Editing the same image again and again with AI usually comes at a cost: each pass shifts the colors a little or wipes details you never asked to change. ByteDance says it trained Seedream 5.5 to keep the regions you don’t edit intact “at the pixel level” and to reduce that accumulated loss.

In the official demo, ByteDance chains 100 edits, and each image starts from the previous one. It begins with a pop-art portrait: a man in a pink coat, colorful rings and a chessboard. Over the rounds, the clothes, the accessories, the objects and even the subject change, and by round 100 only a pawn is left on the board. According to ByteDance, even after that many changes the model still edits small objects precisely, such as rings or glasses frames.

![Official Seedream 5.5 demo with 100 chained edits](/news/seedream55/edits-100.jpg)

[Watch the official video](/news/seedream55/edits-100.mp4)

If you try it on a product photo, run the check the demo can’t run for you: change one thing per pass, such as the background, a color or a line of text, and confirm the logo, the packaging shape and the labels stay the same.

## Transparent backgrounds, no cutout afterwards

Seedream 5.5 generates images with an alpha channel, in RGBA format: the background comes out fully or partly transparent, with no separate tool needed to remove it. In the official video, it creates circular close-ups of a snowy owl with transparent backgrounds, showing its feathers, a claw and an eye, from text and a reference image. It then places those assets over an image of the owl to build an infographic.

![Official demo of transparent-background assets for an infographic](/news/seedream55/owl-rgba.jpg)

[Watch the official video](/news/seedream55/owl-rgba.mp4)

For social media this is one of the most practical additions: stickers, product cutouts for stories or pieces of a carousel or infographic you’ll assemble in CapCut. Partial transparency matters for materials such as glass or sheer fabric, exactly where an automatic cutout tends to fail.

## Clearer small text and more natural photos

According to ByteDance, the third upgrade is about quality: less artificial shine on skin, more natural light and better small text. One of the official examples is this newspaper-style page about Shakespeare, with several blocks of text packed into a small space.

![Newspaper-style page about William Shakespeare generated with Seedream 5.5, with his portrait, a drawing of the Globe Theatre and several readable blocks of small text.](/news/seedream55/text-example.jpg)

*Official ByteDance example. It was chosen for the launch, not picked at random.*

ByteDance also measured its text corruption rate, though it doesn’t say whether it counts per image or what makes an error severe. On severe errors, Seedream 5.5 scores **0.4%**, compared with 2.8% for Seedream 5.0 Pro and 0.7% for GPT Image 2.5 Sunburst:

### Text errors in generated images, according to ByteDance
Text corruption rate in ByteDance’s evaluation (Chinese and English, including dense small text). Lower is better. ByteDance doesn’t say whether it counts per image or what makes an error severe. HeyMark did not run this test.

| Model | Severe errors | Minor errors |
| --- | ---: | ---: |
| Seedream 5.5 | 0.4% | 1.7% |
| Seedream 5.0 Pro | 2.8% | 2.6% |
| Nano Banana 2.1 | 1.7% | 3.0% |
| GPT Image 2.5 Sunburst | 0.7% | 7.4% |

ByteDance’s chart labels the OpenAI model “ChatGPT Image 2.5 Sunburst”. [ByteDance Seed technical blog](https://seed.bytedance.com/en/blog/more-realistic-images-more-stable-editing-across-100-rounds-introducing-seedream-5-5).

Even at low rates, check every word on a poster or a price tag before you publish: a single typo means redoing the piece.

## How it compares, according to ByteDance

ByteDance also asked expert evaluators to compare pairs of images on text structure and realism, both when creating from text and when starting from an image. Against the two rival models, Seedream 5.5 comes out ahead in 7 of 8 comparisons; against Nano Banana 2.1 on text, only narrowly (+3.82% and +5.23%). The exception: **Google’s Nano Banana 2.1 wins on realism when starting from an image**. ByteDance doesn’t publish how many images or evaluators it used.

### Evaluator preference (GSB), according to ByteDance
Expert evaluators compared pairs of images and marked Good/Same/Bad. A positive value favors Seedream 5.5; 0 is parity. ByteDance doesn’t publish how many images or evaluators it used, or the breakdown of answers. HeyMark did not run this test.

#### Text structure

| Seedream 5.5 against | Create from text (T2I) | From an image (I2I) |
| --- | ---: | ---: |
| GPT Image 2.5 Sunburst | +16.01% | +20.72% |
| Nano Banana 2.1 | +5.23% | +3.82% |
| Seedream 5.0 Pro | +5.00% | +18.54% |

#### Realism

| Seedream 5.5 against | Create from text (T2I) | From an image (I2I) |
| --- | ---: | ---: |
| GPT Image 2.5 Sunburst | +37.29% | +36.05% |
| Nano Banana 2.1 | +21.79% | −6.18% |
| Seedream 5.0 Pro | +39.44% | +55.62% |

The OpenAI model in the test is GPT Image 2.5 Sunburst, not GPT-Image-2.6, introduced on November 4. [ByteDance Seed technical blog](https://seed.bytedance.com/en/blog/more-realistic-images-more-stable-editing-across-100-rounds-introducing-seedream-5-5).

Two caveats:

- **The OpenAI rival is GPT Image 2.5 Sunburst.** GPT-Image-2.6, the model behind Images 2.6 that OpenAI [introduced on November 4](/en/guides/news/openai-introduces-images-2-6-with-editing-and-gifs-1c6783ca832b4e698d8085afbe364194/), five days before this launch, is not part of these tests.
- **Every evaluation comes from ByteDance**; the use-case test was run on the MagicArena platform. When this story was written, no independent leaderboard, such as [Artificial Analysis](https://artificialanalysis.ai/image/model-families/Seedream), had ranked Seedream 5.5 yet.

The evaluation also covers six professional uses: e-commerce, marketing, film and TV, gaming, office work and fashion design. Against Seedream 5.0 Pro, the share of images the evaluators rated usable rises in all six, and in film and TV and in office work it more than doubles. The chart doesn’t publish exact figures, but its scale stops at 35%: by that standard, most images were still not considered ready to use.

![Official ByteDance chart with two radar plots. Left: usable-image rate by use case on a 0 to 35% scale, where Seedream 5.5 beats Seedream 5.0 Pro in every case and peaks in film and TV. Right: mean opinion score from 0 to 4, with smaller gains across all six cases.](/news/seedream55/usability-radar.jpg)

*Official ByteDance chart: usable-image rate (left) and mean evaluator score (right), against Seedream 5.0 Pro.*

## Where you can use Seedream 5.5

| Where | How to get there | Conditions |
| --- | --- | --- |
| CapCut, app | Edit Photo → AI Edit, AI Lab or AI Image | Supported regions; US soon |
| CapCut, web | Design Studio and Video Studio | Supported regions; US soon |
| CapCut, desktop | AI Ad Maker and AI Image | Supported regions; US soon |
| Dreamina | Not specified in the announcement | Open to all users; unlimited use for 7 days for everyone and 30 days on Basic and higher plans |
| BytePlus | Businesses | Announced; BytePlus links to its sales contact form |

Menu names are taken from CapCut’s announcement. Sources: [CapCut](https://x.com/capcutapp/status/2119746849917878279), [Dreamina](https://x.com/dreamina_ai/status/2119751497282125949) and [BytePlus](https://x.com/BytePlusGlobal/status/2119741240300470575).

If you have **CapCut Ultra** in the UK, France, Germany, Italy, Spain, Mexico, Brazil, Canada, Japan, South Korea or Australia, you can generate images with Seedream 5.5 without limits from **November 12 to 18**.

ByteDance also plans a **Pro** version of Seedream 5.5, with no date yet.

Dreamina, for its part, cites 95% text accuracy: a Dreamina marketing figure with no published method, separate from the evaluation in the technical blog.

[ByteDance Seed’s original post on X](https://x.com/ByteDanceSeed_/status/2119720475068920181), from November 9, with the launch video.

## Plan your next post in HeyMark.

Keep the idea, review the draft with your team, and see how it performed in the accounts you connected.

[Start free](https://app.heymark.ai) · [See how it works](https://heymark.ai/en/#product)

## Developer and agent resources

- [HeyMark MCP documentation](https://heymark.ai/en/mcp/)
- [llms.txt](https://heymark.ai/llms.txt)
- [Full site content for language models](https://heymark.ai/llms-full.txt)
- MCP protocol endpoint: `POST https://mcp.heymark.ai`
- OAuth protected-resource metadata: [/.well-known/oauth-protected-resource](https://mcp.heymark.ai/.well-known/oauth-protected-resource)
- MCP server card: [/server-card](https://mcp.heymark.ai/server-card)