Google's newest Gemini image model, now in Comfy. Give it a prompt and references, and it returns an image at up to 4K. It works anywhere Nano Banana 2 does, with a new thinking level and a lower price.
Realistic light and detail for the scenes you've only pictured.
Iterate your designs in any style you want.
Advertising for any industry, with crisp detail and type that reads.
Nano Banana 2.1 is Google's newest Gemini image generation and editing model, and the successor to Nano Banana 2. Give it a prompt and optional reference images, and it returns a finished image at up to 4K.
There are two changes: a third thinking level and a lower cost per run. Aspect ratios and resolution tiers carry over, so it fits into your existing workflows in the same slot.
Update ComfyUI, double-click the canvas, and search for the Nano Banana 2.1 node, or open the workflow from the Template Library. If you'd rather install nothing, run it on Comfy Cloud.
Yes. Connect your image and describe the change. Recolors, material swaps, object removal, and text replacement leave the rest of the frame untouched. You can also edit by intent: ask for every metal object to become wood, and the model finds the right ones.
Yes. Use them to guide characters, products, and garments. Character turnarounds and orthographic sheets hold costume, scale, and alignment across every panel. Virtual try-on keeps the subject's identity and pose intact.
Write it like a brief, and spell out every word you want rendered in the image. Name a style to get real stylization. For thinking levels, use Minimal to explore, High for dense layouts or stacked constraints, and Medium in between. Higher levels take longer and use more tokens.
The model is one step, not the whole job. Chain it with upscalers, other partner models, and your own nodes, then rerun with one parameter changed. Every step stays visible and repeatable.
Access cloud-powered ComfyUI workflows with straightforward, usage-based pricing.
Start Comfy Cloud for free. Upgrade when you're ready.
5 free runs on real GPUs — no credit card required.
Billed monthly
Generates ~380 5s videos*
Billed monthly
Generates ~670 5s videos*
Billed monthly
Generates ~1,915 5s videos*
Built for teams collaborating on workflows together.
Billed monthly
Generates ~13,405 5s videos*
Everything in Pro, plus:
Coming soon...
Need more members? Looking for more flexibility or custom features?
*Based on 5s videos created with the Wan 2.2 Image-to-Video template using default settings (81 frames, 18fps, 640x640, 4-step sampler)
Build workflows in the browser today. Batch campaigns with the API, or connect image generation to the rest of your creative pipeline.