Geração de imagem
Disponível agora

Seedream 4.5

por ByteDance

ByteDance's upgraded image model.
Multi‑image references, dense‑text rendering, and character continuity in one unified model.

Seedream 4.5

por ByteDance

Principais recursos

Especificações técnicas

Up to 2K

High-resolution image output

T2I + Edit

Unified generation and editing

Multi-image

Multiple reference inputs supported

Identity + text

Subject continuity, dense text rendering

Casos de uso

Multi-shot brand stories

Generate the same character or product across multiple scenes and angles. Identity stays consistent across ad series and rollouts.

Poster and packaging design

Build posters, packaging mockups, and editorial layouts where dense text and typography need to render cleanly inside the image.

Reference-led composition

Feed in a face, an outfit, and an environment as separate references, then have Seedream 4.5 combine them into a coherent final image.

Image-to-video key frames

Create art-directed key stills here, then carry them into Seedance for animation. The standard ByteDance image-to-video flow on Morphic.

Exemplos de prompts

Multi-reference scene

Combine these references into one image: this character in this jacket, walking through this neon-lit alley, cinematic mid shot, rainy night

Edit prompt

Poster typography

Movie poster, retro 70s thriller, dense small text credits along the bottom, large title across the middle, grainy warm color palette

Edit prompt

Editorial still

Editorial portrait of a woman holding a vintage camera, side window light, muted earth tones, magazine cover composition

Edit prompt

Preços simples

Comece grátis hoje mesmo, com a opção de fazer upgrade ou cancelar quando quiser.

Basic

$9/ mês
cobrado como $0 por ano

900 mensal créditos

1 apenas usuário

Todos os modelos

Workflows

Standard

$24/ mês
cobrado como $0 por ano

3200 mensal créditos

1 apenas usuário

Todos os modelos

Workflows

Pro

$45/ mês
cobrado como $0 por ano

6200 compartilhado mensal créditos

1 usuário

+ até 4 mais com custo adicional

Todos os modelos

Workflows

Pro Max

$170/ mês
cobrado como $0 por ano

24000 compartilhado mensal créditos

1 usuário

+ até 9 mais com custo adicional

Todos os modelos

Workflows

Enterprise

Para limites maiores

Personalizado

termos de preços e cobrança

Créditos ilimitados
Limites de vagas personalizados
Todos os modelos
Workflows
Pricing Gradient

Free

Para experimentar

$0

grátis para sempre

Até 20 créditos
apenas 1 usuário
Modelos limitados
Workflows
Comparar detalhes dos planos

Perguntas frequentes

What is Seedream 4.5?
Seedream 4.5 is ByteDance's upgraded image generation model. It improves prompt adherence, multi-image reference handling, and dense text rendering while keeping text-to-image and editing unified in a single model.
How is Seedream 4.5 different from Seedream 4?
ByteDance positions 4.5 as an all-round improvement through overall scaling of the model, sharper detail preservation across multi-image references, enhanced typography and dense text rendering, and designer-level composition. Use 4.5 when identity continuity or typography in the image matters.
Does Seedream 4.5 support multi-image input?
Yes. You can pass in multiple reference images, the model identifies the main subject in each and composes a coherent output that preserves the important details from every reference.
How do I use Seedream 4.5 on Morphic?
Open Copilot, attach your references, describe the result, and pick Seedream 4.5. It's a strong default for brand series, poster work, and any prompt where the same subject needs to appear consistently across multiple images.
Can I edit images with Seedream 4.5?
Yes. The same model handles both text-to-image and image editing, so you can generate a base, then refine with targeted edits in the same conversation.
When should I pick Seedream 4.5 vs Seedream 5.0?
Use Seedream 4.5 when you want fast, high-fidelity multi-image composition and clean text rendering. Use Seedream 5.0 when you need the model to reason carefully, pull in current real-world context, or learn from example-based edits.

Outros modelos

Explore o restante do catálogo de modelos do Morphic.

Ver todos os modelos →

Seedream 5.0 Pro

ByteDance

Edição precisa por região e separação em camadas. Infográficos densos e texto nativo em 14 idiomas.

Seed Audio 1.0

ByteDance

O modelo de áudio all-in-one da ByteDance. Voz, música e efeitos sonoros em uma única geração.

Seedance 2.5

ByteDance

O novo modelo de vídeo de próxima geração da ByteDance. Até 30s de clipes nativos, 50 referências, 4K.

Bernini

ByteDance

O modelo de código aberto da ByteDance para editar vídeos com instruções em texto, mantendo a identidade intacta.