WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/Seedance Video Models/bytedance/seedream-v4/sequential

text-to-image

bytedance/seedream-v4/sequential

Seedream 4.0 is a state-of-art image model by Bytedance. Seedream 4.0: Surpassing nano banana
in every aspect.

Doc
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 image to be generated and uploaded before returning the response. It allows you to get the image directly in the response. This property is only available through the API.

Idle

Generate a set of 4 consecutive illustrations, capturing a high-octane giant robot battle in a classic mecha anime style, from two massive mechs charging at each other in a ruined cityscape, to a dynamic clash of energy swords creating a shower of sparks, a close-up on a pilot's determined face inside the cockpit, and the final explosive shot of the victorious mech standing over its defeated foe.

Your request will cost $0.03 per run.

For $1 you can run this model approximately 33 times.

One more thing:

ExamplesView all

Generate a set of 4 consecutive illustrations, capturing a high-octane giant robot battle in a classic mecha anime style, from two massive mechs charging at each other in a ruined cityscape, to a dynamic clash of energy swords creating a shower of sparks, a close-up on a pilot's determined face inside the cockpit, and the final explosive shot of the victorious mech standing over its defeated foe.
Generate a set of 4 consecutive illustrations, detailing the life cycle of a butterfly, from a tiny egg on a leaf, to a caterpillar, then to a chrysalis, and finally to a beautiful butterfly.
Generate a set of 4 consecutive illustrations, depicting the awe-inspiring moment an astronaut on a desolate alien planet discovers life, from their lone rover cresting a crater rim, to noticing a faint, bioluminescent glow in the darkness below, then cautiously approaching a cave entrance pulsating with light, and finally the breathtaking reveal of a vast, glowing subterranean forest inside.
Generate a set of 4 consecutive illustrations, showing the growth of a sunflower from a seed sprouting, to a young plant, then to a budding flower, and finally to a full bloom facing the sun.
Generate a set of 5 consecutive illustrations: A close-up of a cheerful person with short, dark hair and wearing a yellow bucket hat and an orange t-shirt, holding up a light blue smartphone as if taking a selfie. Their backpack strap is visible over their shoulder. The background is slightly blurred but hints at an outdoor setting. The person from the first image is now shown from the waist up, their arm extended holding the smartphone, capturing a selfie. Behind them, a vibrant cityscape begins to emerge, featuring traditional Chinese architecture like a temple with a blue roof, and modern skyscrapers, including the recognizable Oriental Pearl TV Tower. A river flows in the midground. A wider shot reveals the full scene: the person is standing in a lush green park by a river. The impressive skyline of Shanghai stretches across the background, showcasing a blend of historical and futuristic buildings. A high-speed train is visible on an elevated track to the right, adding a sense of movement to the modern urban landscape. A panoramic view of the Shanghai cityscape from the park's perspective, without the person. The traditional temple, gleaming skyscrapers, the Oriental Pearl TV Tower, the river, and the elevated train track are all prominently featured. The park's greenery fills the foreground. A slightly zoomed-out panoramic shot, emphasizing the grand scale of the Shanghai skyline at sunset, with warm colors reflecting on the buildings and the river. The high-speed train is now a blur in the distance, and the park is a beautiful, serene space in the foreground.
Generate a set of 6 consecutive illustrations, in a slapstick cartoon style, detailing a comical chain of events started by a cat chasing a mouse, showing the mouse darting under a table, the cat crashing into the table leg, which causes a vase of water to tip over, spilling on a sleeping dog, who then jumps up in surprise and runs through the house, leaving a trail of wet paw prints everywhere.
Generate a set of 4 consecutive illustrations, in a soft, dreamy bedtime story style, depicting a tiny star who wishes to visit Earth, showing the little star twinkling brightly in the vast sky, then gently falling as a shooting star, landing softly in a child's backyard, sparkling on the grass for a moment, and finally wishing the child sweet dreams before twinkling back up to its home.
Generate a set of 5 consecutive illustrations, in a clean, minimalist sci-fi style, showing a factory robot's journey to consciousness, from performing a repetitive task on an assembly line, to a moment of hesitation as it observes a bird outside the window, then it deviating from its programming to gently touch the glass, followed by it looking at its own metallic hands with a new sense of wonder, and the final scene of it stepping out of the factory into the dawn of a new world.
Generate a set of 4 consecutive illustrations, in a whimsical, fantasy art style, personifying the changing of seasons, depicting the gentle Autumn Spirit handing over a golden leaf to the sleeping Winter Spirit, who then awakens, blanketing the landscape in frost and snow, followed by the energetic Spring Spirit arriving to melt the ice with a touch, and finally the vibrant Summer Spirit laughing as they bring forth a bounty of flowers and sunshine.

README

Seedream 4.0 is a state-of-art image model by Bytedance. Seedream 4.0: Surpassing nano banana in every aspect.

Multi-modal image generation support: Seedream 4.0 is the first to support multi-modal image generation, enabling text-to-image, image-editing, and group image generation with a single model.

Outstanding model advantages: It features five major highlights: precise instruction editing, high feature retention, deep understanding ability, ultra-fast inference speed, and ultra-high-resolution output. For example, it takes as little as 1.8 seconds to generate a 2K image in text-to-image mode.

Diverse scene applications: Covers various scenarios such as commercial design (including posters, brand clothing, packaging, e-commerce, etc.), entertainment (such as anime and movie roles), fine art, architectural design, and more. It supports various complex editing operations, such as object addition and deletion, attribute change, style change, structural adjustment (e.g., face swapping), etc.

Prompt writing guide: Use clear and specific instructions following the formula of "change action + change object + target feature." While generating multiple images, use words like "a series of," "group of images" to maintain consistency.

Text-to-image writing guide: The image content in coherent natural language and group images for a specific scene description. Use professional vocabulary in its original language and special image terms to match the scene description.

Problem self-check list: Identify common problems such as incorrect instructions, inadequate description, missing details, or redundant instructions. It recommends rechecking image editing objects, and insufficient aesthetic effects, and enhancing background consistency.

Rich editing functions: It includes style/image editing (element addition and deletion, frame/brush editing, style transformation, texture replacement, etc.), structural editing (object structure modification, object reshaping, etc.), and feature editing (color tone, detail transformation, attribute adjustment, etc.).