Seedream 4.5 for one 2K or 4K image from text or as many as 14 reference images.
Brands
ByteDance
Seedance video and Seedream image families for production-oriented media creation.
Models
Image
Seedream 4.5
View details →Seedream 4.5 creates images from text and edits them from as many as 14 reference images. ByteDance emphasizes faithful preservation of faces, lighting, color, and other reference details, along with improved multi-image composition and readable dense text. The Omnipix integration returns one 2K or 4K image per request and supports preset aspect ratios or the proportions of the first reference.
Seedream 5
View details →Seedream 5 accepts a text prompt for new images and optional image references for editing or style guidance. Pro configurations expose 1K and 2K output, while Lite is oriented around 2K and 3K output and includes separate generation and editing entries in this catalog. Up to ten references may be used, but fewer well-chosen images usually make each reference's purpose easier to communicate.
Seedream 5 Lite entry dedicated to image editing with one or more references.
Seedream 5 Lite text-to-image generation with 2K or 3K output.
Seedream 5 Pro generation and reference editing with 1K or 2K output.
Seedream 5 Pro LR with less-restrictive prompt filtering, including requests up to NSFW level.
Models
Video
Seedance 1.5
View details →Seedance 1.5 Pro is ByteDance's joint audio-video model for text-driven and image-driven clips. It is designed for prompts that combine action, camera direction, dialogue, ambient sound, and music, and can use first and last frames to constrain the visual transition.
Seedance 1.5 Pro generates synchronized video and audio from text or image guidance.
Seedance 2
View details →Seedance 2.5 combines text-only generation with optional image, video, and audio guidance in one flagship task. It supports 480p and 720p output from 4 to 15 seconds, with up to nine images, three videos, and three audios. Seedance 2.0 remains available in Full, Fast, and Mini tiers; each has an LR counterpart with more permissive prompt filtering when avoiding false refusals matters.
Recommended
Standard Seedance may refuse harmless prompts and synthetic people. Start with LR for substantially fewer moderation false positives; choose Full LR, Fast LR, or Mini LR for the quality and speed you need.
Seedance 2.5 flagship generation from text with optional image, video, and audio references.
Seedance 2.0 Pro with native audio, first/last-frame control, and multimodal image, video, and audio references.
Recommended for prompt reliability: full-quality Seedance 2.0 with substantially fewer false refusals, including benign scenes with synthetic people.
Start here when ordinary Seedance rejects harmless prompts. Full LR keeps full quality with substantially more permissive filtering—even for synthetic people and requests up to NSFW level—subject to platform rules.
Faster Seedance 2.0 workflow with the same text, frame, multimodal-reference, and native-audio input structure.
Recommended for rapid iteration with fewer prompt refusals: faster Seedance 2.0 and the more permissive LR moderation profile.
Choose Fast LR for quicker iterations with substantially fewer false prompt refusals, including benign synthetic-person scenes. Requests up to NSFW level are supported subject to platform rules.
Seedance 2.0 Mini for economical text, frame-guided, and multimodal-reference generation.
Recommended for economical exploration with fewer prompt refusals: compact Seedance 2.0 with the more permissive LR profile.
Choose Mini LR for lower-cost exploration with substantially fewer false prompt refusals, including benign synthetic-person scenes. Requests up to NSFW level are supported subject to platform rules.