商品目录

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

原站按任务参数或阶梯规则计价，请在原站选择具体规格。

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

即梦4 绘图，Dalle 格式

豆包官方直连！支持调整出图数量(n)、尺寸(size)、绘画模式(type)及AI水印(watermark)，并支持上传底图进行创作。例如：画一只未来世界的机械猫 -n=2 -size=2k。

即梦4 绘图，Dalle 格式

原站按任务参数或阶梯规则计价，请在原站选择具体规格。

Seedream 4.0 is a state-of-the-art (SOTA) multimodal image creation model based on a leading architecture. Its generated aesthetics, instruction compliance, structural integrity, and subject consistency are among the world's best. The model uses a unified architecture to unify text-to-image and editing capabilities, natively supporting text, single-image, and multi-image input. Through deep reasoning based on prompts, it automatically adapts to the optimal image aspect ratio and generation quantity, and can continuously output up to 15 content-related images at once, supporting 4K ultra-high-definition output.

即梦4 绘图，Dalle 格式

原站按任务参数或阶梯规则计价，请在原站选择具体规格。

原站按任务参数或阶梯规则计价，请在原站选择具体规格。

Seedream 4.0 is a state-of-the-art (SOTA) multimodal image creation model based on a leading architecture. Its generated aesthetics, instruction compliance, structural integrity, and subject consistency are among the world's best. The model uses a unified architecture to unify text-to-image and editing capabilities, natively supporting text, single-image, and multi-image input. Through deep reasoning based on prompts, it automatically adapts to the optimal image aspect ratio and generation quantity, and can continuously output up to 15 content-related images at once, supporting 4K ultra-high-definition output.

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

Seedream 4.0 是豆包/即梦图像生成与编辑型号，适合中文海报、商品图、插画和视觉设计。支持 OpenAI Chat、图像生成与图片编辑接口；新人应在提示词中明确画幅、主体、风格和文字内容。

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。

原站按任务参数或阶梯规则计价，请在原站选择具体规格。

Seedream 4.0 is a state-of-the-art (SOTA) multimodal image creation model based on a leading architecture. Its generated aesthetics, instruction compliance, structural integrity, and subject consistency are among the world's best. The model uses a unified architecture to unify text-to-image and editing capabilities, natively supporting text, single-image, and multi-image input. Through deep reasoning based on prompts, it automatically adapts to the optimal image aspect ratio and generation quantity, and can continuously output up to 15 content-related images at once, supporting 4K ultra-high-definition output.

原站公开的站内额度标价；充值折扣、规格附加费及最终扣费以原站为准。