Seedream 4.5
Seedream 4.5 is a ByteDance image generation model that supports reference image inputs and custom output dimensions.
ByteDance
WaveSpeedText-to-image generation with reference image support
Seedream 4.5 is an image generation model developed by ByteDance and made available through the WaveSpeed provider. It accepts text prompts alongside optional reference images, allowing users to guide generation with a source image rather than relying on text alone. The model supports configurable output dimensions via width and height inputs, giving developers control over the aspect ratio and resolution of generated images.
Seedream 4.5 is suited for workflows that require image-to-image guidance, such as style transfer, product visualization, or creative iteration from an existing visual reference. It is priced at $0.04 per image and operates with a 2,000-token context window for prompt input. The model is available on MindStudio without requiring separate API key management, making it accessible for integration into AI-powered applications.
What Seedream 4.5 supports
Image Generation
Generates images from text prompts, with a 2,000-token context window available for describing the desired output.
Reference Image Input
Accepts one or more source images as URL arrays to guide the generation, enabling image-to-image style workflows.
Custom Output Dimensions
Supports explicit width and height parameters so developers can control the exact pixel dimensions of generated images.
Per-Image Pricing
Billed at a flat rate of $0.04 per image with no minimum commitment, making cost predictable for high-volume generation tasks.
Ready to build with Seedream 4.5?
Get Started FreeCommon questions about Seedream 4.5
How much does Seedream 4.5 cost to use?
Seedream 4.5 is priced at $0.04 per generated image, regardless of resolution or prompt length.
What is the context window for Seedream 4.5?
The model supports a context window of 2,000 tokens, which applies to the text prompt used to describe the desired image.
Can I use a reference image with Seedream 4.5?
Yes. The model accepts an array of image URLs as input, allowing you to supply one or more reference images to guide the generation output.
Can I control the size of the generated image?
Yes. Seedream 4.5 accepts explicit width and height values as numeric inputs, so you can specify the output dimensions for each generation request.
Who publishes Seedream 4.5 and where is it hosted on MindStudio?
Seedream 4.5 is published by ByteDance and served through the WaveSpeed provider. On MindStudio it is available without requiring a separate API key.
What people think about Seedream 4.5
Community discussions around Seedream 4.5 show notable interest in its performance benchmarks, with a dedicated benchmark thread receiving 94 upvotes and 28 comments on r/singularity. Users have also run direct prompt comparisons between Seedream 4.5 and competing models, reflecting active interest in evaluating its output quality.
Some threads reference competing models reaching higher leaderboard positions after Seedream 4.5's release, suggesting the competitive landscape shifted quickly following its December 2025 launch. Discussions tend to focus on image quality comparisons and generation speed rather than editing or text rendering use cases.
bytedance dropped seedream 4.5, ran it against nano banana pro on same prompt
Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview) takes #1 in Text to Image in the Artificial Analysis Image Arena at half the price of Nano Banana Pro!
Performance Benchmark Seedream 4.5
Qwen released Qwen-Image-2512 on Hugging face. Qwen-Image-2512 is currently the strongest open-source model.
Documentation & links
Parameters & options
Explore similar models
ByteDanceSeedream 5.0 Pro
Seedream 5.0 Pro is an image generation model from ByteDance that supports source image input and flexible aspect ratio and resolution controls.
ByteDanceSeedream 4.0
Seedream 4.0 is an image generation model from ByteDance that accepts text prompts and source images to produce generated images.
ByteDanceSeedream 5.0 Lite
Seedream 5.0 Lite is a ByteDance image generation model that accepts source images and custom dimensions at $0.035 per image.
X.aiGrok Imagine 2.0
Grok Imagine 2.0 is an image generation model from X.ai that accepts source images and supports configurable aspect ratio, resolution, and quality.
MetaMuse Image
QwenQwen Image 3.0
Qwen Image 3.0 is an image generation model from Qwen that supports text prompts and source image inputs at $0.03 per image.
Start building with Seedream 4.5
No API keys required. Create AI-powered workflows with Seedream 4.5 in minutes — free.