Skip to main content
Text to Image

Seedream v4 Text-to-Image

Generate images using ByteDance Seedream v4 text-to-image model

View details
Try it in Ampere

Inputs

Loading input fields...
Execution Steps

Loading workflow structure...

Loading curated examples...

Overview

Seedream v4 Text-to-Image turns a written prompt into generated images using ByteDance's Seedream v4 model. Use it for campaign concepts, ad and social visuals, landing-page art, product storytelling, and prompt-only visual exploration with flexible preset, auto, or custom sizing.

Use cases

  • Generate visual directions for a landing page, ad, launch campaign, or social post.
  • Explore prompt-enhanced drafts with standard or fast enhancement.
  • Create several image options from one brief by varying size, seed, or output settings.
  • Use auto, 2K, 4K, preset, or custom sizing when layout needs are still being tested.

Input tips

  • Write a clear prompt with subject, setting, visual style, composition, and intended use.
  • Use image_size presets such as square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, auto, auto_2K, or auto_4K.
  • For custom image_size, use width and height from 1024 to 4096 pixels.
  • Set num_images and max_images from 1-6; higher max_images can return more options per generation.
  • Use enhance_prompt_mode standard for quality-oriented prompts or fast for quicker basic enhancement.
  • Use seed when repeatable generation matters, and leave the safety checker enabled for normal use.

Expected output

The AI Tool returns one or more generated image URLs with optional content type, file name, file size, width, and height, plus the seed used and cost metadata. The shared Seedream output view renders a single image or gallery and shows seed, image count, and the Seedream v4 model label.

Caveats

  • This AI Tool generates from text only; use Seedream v4 Image Editor when source images should guide the result.
  • Custom image sizes must use width and height from 1024 to 4096 pixels.
  • Prompt enhancement can change how the brief is interpreted.
  • Higher num_images or max_images settings can return more files and take longer to review.
  • Safety filtering can alter or block some requests.
  • Generated text, logos, product details, faces, and image edges should be reviewed before use.

Related AI Tools