Nano Banana 2.1: Text to Image
Generate images from text prompts using Nano Banana 2.1, Google's fast Gemini-based image model, delivering one finished image with no input files required. Ideal for brand marketing posters, e-commerce product visuals, and IP character series.
简介
This ComfyUI tutorial workflow, Nano Banana 2.1: Text to Image, is a minimal, fast text-to-image pipeline built around two nodes: ByteDanceSeedreamNodeV3 for image generation and SaveImageAdvanced for output. Your prompt flows directly into ByteDanceSeedreamNodeV3, which calls a remote API backend labeled "Nano Banana 2.1" to synthesize a single image without requiring any input files. Typical controls on this node include prompt/negative prompt, width/height, and seed for reproducibility (exact options depend on your installed node version and provider limits).
你需要提供
- 正在读取工作流
在 ComfyUI 中运行。 此工作流无法在本页面运行。你可以在 Comfy Cloud 中打开（已预先加载所需内容），或下载后在自己的 ComfyUI 中使用。
在 Cloud 中试用常见问答
In most setups, yes. ByteDanceSeedreamNodeV3 queries a remote service. Open the node’s settings and add your API key and endpoint as instructed by the node provider. If you see authentication errors, verify the key, endpoint, and any usage limits.
Set a fixed seed value in ByteDanceSeedreamNodeV3 and keep prompt, resolution, and other parameters unchanged. SaveImageAdvanced can embed metadata so you can recall exact settings later.
Adjust width/height in ByteDanceSeedreamNodeV3, but stay within limits enforced by the backend (often specific max dimensions or aspect ratios). If a size isn’t allowed, the node will typically return an error—reduce dimensions or try a common aspect like 1:1, 3:4, 4:3, or 16:9.
This workflow is set to produce one image. To batch, duplicate the generation path or add a batching/loop construct feeding multiple prompts or seeds. For upscaling, add an upscaler node (e.g., ESRGAN/4x-UltraSharp) after ByteDanceSeedreamNodeV3 and route its output to SaveImageAdvanced.