Try Google Gemini Omni Flash Video Generator from Google →
Models
Agents
WorkflowsStudioPricingBlogDocs
ExploreDiscover models by categoryBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Explore models/
Image GenerationActive

ByteDance / seedream-v4-5

seedream-v4-5

bybytedance

Access the Seedream 4.5 API for fast high resolution image generation and editing. Simple integration, clear pricing, and support for text to image, multi image input, and advanced creative workflows.

Text to ImageImage to Image
Model ID
seedream-v4-5
Provider
bytedance
Runs
21664
Updated
1779109220
seedream-v4-5
21664
Runs
3
Comments
Average rating : 5 (3 users)
Providerbytedance
Modelseedream-v4-5
Runs21664
Text to ImageImage to Image
wiro playground—bytedance/seedream-v4-5
Reset to defaults
Delete All
0 / 14
Maximum 14 image allowed
Drop image to upload

OR

Click to browse your device

Supports: JPG, JPEG, PNG, GIF, WEBP, HEIC

Optional list of input image URL(s) and/or file(s) for creating, editing or combining images

Please provide how many images you want to generate in the prompt. Edit max images according to it.

Sample outputs
Sample 1
Sample 2
Sample 3
Sample 4
Click To See More Samples
Updated 1779109220

Seedream v4.5 is ByteDance's most advanced image generation model, designed to deliver superior consistency by accurately preserving subject details, lighting, and color tones during complex edits. It features significant upgrades in portrait refinement, small-text generation, and multi-image composition, enabling the seamless fusion of styles and elements from multiple inputs. With native support for sequential batch generation, v4.5 optimizes reasoning and visual aesthetics to bring creative ideas to life with high artistic precision and coherence.

Example prompts

Great starting points for seedream-v4-5.

Using this LOGO as a reference, create a visual design system for an AI API provider named WIRO, including packaging bags, hats, cards, lanyards, etc. Main visual tone is green, with a fun, simple, and modern style.Image Generation
Replace the clothing in image 1 with the outfit from image 2.Image Generation
Generate a set of 4 images featuring the same young female astronaut character in a futuristic white spacesuit.\\n1- Portrait of her holding her helmet, smiling in a brightly lit space station corridor.\\n2- Her floating in zero-gravity inside the cockpit, looking out the window at a blue nebula.\\n3- Her walking on the surface of a dusty red planet, wind blowing dust around her boots.\\n4- Close-up of her face illuminated by the glow of a holographic map she is examining.Image Generation
A surreal portrait of a lion made entirely of swirling liquid mercury. The lion is roaring, and droplets of silver liquid are flying off its mane, suspended in mid-air. The background is a solid matte black to contrast with the high reflection of the metal. Studio lighting, ray-traced reflections, fluid simulation aesthetics, high detail.Image Generation
A futuristic eco-brutalist residential tower covered in vertical hanging gardens, located in a rainy cyberpunk Tokyo street at night. Neon signs reflect off the wet pavement. The building features raw concrete mixed with bioluminescent plants. Shot from a low angle to emphasize scale, volumetric fog, moody atmosphere, photorealistic, architectural digest style.Image Generation

API quick start

Run seedream-v4-5 with a single API call.

POST https://api.wiro.ai/v1/Run/ByteDance/seedream-v4-5
{
  "prompt": "Replace the clothing in image 1 with the …",
  "maxImages": 1,
  "watermark": "false",
  "inputImage": "https://your-cdn.com/input.png"
}
View full API docs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
Getting StartedIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion