> For the complete documentation index, see [llms.txt](https://help.fixfolio.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.fixfolio.ai/en/tip/models.md). # \[Banner Creation] Image Drawing Model Selection Guide ## 🎨 Image Drawing Model Comparison Previously provided `NanoBanana 2` along with the model, a new model `GPT Image 2` has been added. Now you can directly choose a model to create banners according to the style of the result you want and the purpose of production. Please refer to the features of each model below and use them as appropriate for your situation. ### (1) NanoBanana 2 (existing model) **Fast creation speed and reference-based style expression**is an image generation model with strengths in. **It reflects the mood and style of the selected reference relatively faithfully**and is suitable for quickly generating **multiple drafts**in the direction you want. It also **intuitively reflects revision requests and direction of production**so, **it can be effectively used when detailed edits are needed or when you want to create stable results centered on references** . ### (2) GPT Image 2 (new model) **Product details and rich expression**is an image generation model with strengths in. **It can more naturally and clearly express elements that were difficult to represent with existing models, such as small text or package copy**. Also, rather than simply imitating reference images **it excels at newly reinterpreting them to match the brand and product characteristics**, making it suitable for **creating more creative and polished advertising visuals**. ### (3) NanoBanana 2 VS GPT Image 2 comparison table

Item	NanoBanana 2 (existing model)	GPT Image 2 (new model)
Example image
Recommended use	Fast production / reference-based production / detailed edits	Banner production where detail and rich expression are important
Result characteristics	Consistent and intuitive style centered on the reference	Rich and varied directional expression with a detailed and clear style
How references are reflected	Reflects the reference style and mood relatively faithfully	Reinterprets the reference to suit the product and situation
Text expression	Small text may be somewhat unnatural	Small text and package copy are expressed stably
How detailed edits are reflected	Reflects requests relatively directly and faithfully	Reflects requests while naturally reinterpreting them to fit the overall mood
Generation speed	Fast	Somewhat slow

## 🤔 Which model should I choose? If you want to quickly implement the reference style `NanoBanana 2`, and if detail and creative direction are important `GPT Image 2`, we recommend ### 🚀 \[NanoBanana 2] When you want to quickly implement the reference style * When you want to create something as similar as possible to the reference feel and style * When you want to quickly generate multiple drafts and check the direction * When you want to directly and faithfully reflect revision requests ### 🔎 \[GPT Image 2] When detail and creative direction are important * When rich and more creative directional expression is needed * When expression of small text or package copy is important * When you want a result that is based on the reference but newly reinterpreted to fit the brand and product {% hint style="info" %} Current image drawing model selection is **supported in banner creation, style expansion, and detailed edits**. **Model selection in Variations is currently being prepared**and will be supported in a future update. {% endhint %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://help.fixfolio.ai/en/tip/models.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.