Imageseedream-v45bytedance-seedream-v4.5

Bytedance Seedream v4.5

Seedream-v4.5 is ByteDance’s advanced text-to-image diffusion model designed for generating high-detail, high-contrast, cinematic and stylized images. It excels at surreal fantasy concepts, sci-fi worlds, product visuals, photoreal scenes, and artistic compositions with strong prompt adherence and crisp detail.

Open in Image Lab Browse all models~5 credits per run

Seedream guideVerified

ByteDance's image line, sibling to the Seedream edit (Seededit) variant. Strong photoreal scene composition and creative visuals.

Strengths

Premium photoreal scene composition — environments feel believable.
Strong on detailed atmospheres (mist, smoke, lighting layers).
Seedream v5.0 jumped quality significantly over v4.

Best for

Detailed environment + subject scenes
Atmospheric / cinematic stills

Prompting tips

Layer your description: environment first, subject second, lighting third, mood fourth.

Parameters

seed
int
Random seed to control the stochasticity of image generation.
image_size
string
The size of the generated image. Width and height must be between 1920 and 4096, or total number of pixels must be between 2560*1440 and 4096*4096.
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9auto_2Kauto_4K
default: [object Object]
max_images
int
If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` …
default: 1
range: 1 … 6
num_images
int
Number of separate model generations to be run with the prompt.
default: 1
range: 1 … 6
enable_safety_checker
boolean
No description.
default: true

You'll need

A text prompt

Try now

More from seedream-v45

Bytedance Seedream v4.5 Edit

bytedance-seedream-v4.5-edit