AI · Article
ByteDance Unveils Seedream 5.5, Image Model That Holds Up Over 100 Edits
AI타임스 ·

At a glance
ByteDance has released Seedream 5.5, a new image generation model. It keeps images intact across many rounds of editing and improves transparent backgrounds and text rendering. The focus is on making it easier to use in design and content production.
Key points
- ByteDance showed the same image edited 100 times in a row while unedited areas kept their colors and details.
- The model can directly create transparent-background images, reducing the need to remove backgrounds by hand.
- It renders complex and small text more accurately and adds more realistic skin, materials, and lighting.
- In its own tests, the serious text error rate fell from 2.8% to 0.4%, but it trailed Nano Banana 2.1 at editing existing images.
Why it matters
Designers and content creators can use AI-generated images more directly in real work. Seedream 5.5 will roll out in stages to platforms such as Dreamina and Doubao.
Original source
바이트댄스, 100회 수정해도 이미지 유지하는 '시드림 5.5' 공개
AI타임스 · Nov 10, 17:20 KST
Read on AI타임스 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to AI타임스.
Other coverage
ByteDance · Ranking and more news
More from this field
- Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST