imagineart-1.5-preview/text-to-image
Transform written ideas into lifelike visuals with precise texture, light, and typography control for professional design use.
Nano Banana 2 Lite Edit is the cost- and speed-focused editing model in Google's Gemini image lineup. You upload one or more images, describe the change in words, and the model returns a revised 1K (1024x1024) picture, usually within a few seconds. Because it favors low latency over maximum resolution, it is built for high-volume, iterative editing rather than slow one-off renders.
On this RunComfy page you work with the editing side of the model. Send a prompt plus your source images, pick an aspect ratio, and receive the edited image URL in the standard prediction response. Multiple uploads can act as references, so the model has more context when applying a guided change.
Output format: Resolution: 1K (1024x1024) / fps: n/a / duration: n/a / aspect ratio: auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8 / audio: n/a
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | — | — | Natural-language instruction describing the edit to apply. |
| image_urls* | Yes (*) | array | — | 1-10 images | Source images to edit or to use as references. |
| aspect_ratio | No | string | auto | auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8 | Output aspect ratio; auto follows the source image. |
Output is a flat $0.035 per image at 1K (1024x1024). Aspect ratio does not change the price, and each returned image bills at the same rate.
Transform written ideas into lifelike visuals with precise texture, light, and typography control for professional design use.
Replace a photo’s background with a new scene using Ideogram 3.
Fast, photorealistic image repair and refinements for product visuals.
Create cohesive 4K visuals with stable subjects and refined scene alignment.
Edit images precisely and fast with FLUX Kontext Pro.
Advanced text-to-image system with LoRA adapters, style control, and photoreal accuracy for design professionals.
Nano Banana 2 Lite Edit is a fast, lightweight image editing model that reworks uploaded images from natural-language instructions. It is designed for prompt-based changes such as background swaps, style shifts, and object cleanup, returning a 1K edited image in the standard prediction response.
Nano Banana 2 Lite Edit is the speed- and cost-focused option, tuned for low latency at a fixed 1K resolution. The standard Nano Banana 2 Edit trades some speed for higher-resolution output options and stronger overall quality, so the Lite variant fits high-volume, iterative work where turnaround matters most.
Yes. Nano Banana 2 Lite Edit accepts one or more uploaded images, up to ten, which can be edited directly or used as references to guide a result. Providing several images gives the model more context when applying a specific change.
Nano Banana 2 Lite Edit handles background and scene swaps, lighting and mood changes, color and style adjustments, and product photo refinement well. For the most reliable results, state what should stay fixed and localize the change you want in the prompt.
Nano Banana 2 Lite Edit returns 1K (1024x1024) images and supports a range of aspect ratios, including common square, portrait, and landscape shapes plus extreme cuts like 4:1 and 8:1. Leaving the aspect ratio on auto lets the model follow the source image; check the RunComfy parameter panel for the full list.
A prompt and at least one source image are required, and up to ten images can be supplied. Output is fixed at 1K rather than higher resolutions, so if you need larger renders, consider a higher-tier model in the same family.
Yes. You can prototype Nano Banana 2 Lite Edit in the RunComfy model UI and then call the same model via the RunComfy API with identical parameters. This lets you move from manual testing to automated image editing without hosting or scaling the model yourself.
Nano Banana 2 Lite Edit bills a flat $0.035 per output image at 1K, and aspect ratio does not change the price. Generations draw from your RunComfy usd or credit balance, and new users typically start with a free trial amount.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
