WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/bytedance/seedream-v4.5
text-to-image

text-to-image

Seedream 4.5 ByteDance | Text-to-Image Generation with Typography & 4K Resolution | WaveSpeedAI

bytedance/seedream-v4.5

Seedream 4.5 by ByteDance is a state-of-the-art text-to-image model with all-round improvements through model scaling. Features enhanced typography, clear text rendering for posters and brand visuals, superior prompt adherence, and up to 4K resolution. Ready-to-use REST API with best performance and no coldstarts.

width
height
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Idle

Nighttime outdoor photoshoot: A young man standsinside a public phone booth, holding a blue phonereceiver to his ear. One hand is casually tucked into his pocket, and he strikes a relaxed posture. He wears a white T-shirt with a pattern, loose brown pants, and jacket draped over his arm. The booth's glass reflects city streetlights with a bokeh effect, creating a vintage film style.

Your request will cost $0.04 per run.

For $1 you can run this model approximately 25 times.

One more thing::

ExamplesView all

Nighttime outdoor photoshoot: A young man standsinside a public phone booth, holding a blue phonereceiver to his ear. One hand is casually tucked into his pocket, and he strikes a relaxed posture. He wears a white T-shirt with a pattern, loose brown pants, and jacket draped over his arm. The booth's glass reflects city streetlights with a bokeh effect, creating a vintage film style.
Golden hour rooftop gathering, 16:9, 4K. A group of four friends with diverse skin tones sit and stand around a low table on a city rooftop café, laughing and talking, no visible brands or logos. Use the provided reference portraits (if any) to keep their faces, hairstyles and outfits consistent. Warm sunlight from the side, soft rim light on hair and shoulders, blurred city skyline in the background, string lights glowing above. Casual modern outfits with natural wrinkles and fabric texture, realistic skin details, subtle makeup. Cinematic lifestyle photography, shallow depth of field, slight film grain, clean composition, publish-ready campaign image.
Afternoon side light illuminates the camping tent, withthe rough texture of the tent canvas clearly visible. AGerman Shepherd lies inside; its owner squats down to shake hands with it.
Five shimmering goldfish weave through crevicesbetween stones; four are red-and-white, while one issilver-white.By the pond's edge, a golden shadedBritish Shorthair cat watches them intently, counting onblind luck. Watercolor style

README

bytedance/seedream-v4.5 (Text-to-Image)

Seedream 4.5 is ByteDance's latest image generation model, achieving all-round improvements through comprehensive model scaling. It excels at typography, poster design, and brand visual creation with superior prompt adherence and aesthetic quality.

Model Highlights

  • Enhanced Typography: Clear and readable text rendering, ideal for posters, logos, and brand visuals
  • Designer-Level Composition: Advanced poster layout capabilities with professional typographic hierarchy
  • Superior Prompt Adherence: Improved alignment between input descriptions and generated outputs
  • High Resolution: Supports up to 4K (4096×4096) resolution output
  • Aesthetic Excellence: Significant improvements in visual quality benchmarked on MagicBench

Use Cases

  • Poster and banner design with embedded text
  • Brand visual and logo creation
  • E-commerce product imagery
  • Social media content with typography
  • Marketing campaign visuals

Price

Only $0.04 per image!

How to Use

  1. Enter your prompt: Describe the subject, layout, text placement (title/subtitle), and style
  2. Set size: Choose width/height up to 4096×4096
  3. Run: Click Run to generate your image

Recommended Resolutions

Aspect RatioResolution (W×H)
1:11024 × 1024
3:21216 × 832
4:31152 × 896
16:91344 × 768
2K (1:1)1448 × 1448
4K (1:1)4096 × 4096