> For the complete documentation index, see [llms.txt](https://sogni.gitbook.io/sogni-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sogni.gitbook.io/sogni-docs/sogni-studio/creating-images/enhancing-images.md). # Enhancing Images ## Image Enhancement Image Enhancement applies **Supernet-powered** refinement to an existing image using two tools: 1. **Creative Enhance** — creative, strength-based enhancement (can intentionally change the image) 2. **Generative Filters** — category-based “filters” powered by a next-gen editing/mixing model that keeps the subject consistent All enhancement options are designed to feel like *editing*, not re-rolling from scratch: you start from an existing image, choose an enhancement, and get a new improved variant. You can access all enhancing options from: • The Enhance menu within the app's main menu options.\ • The Enhance button on the main window's toolbar.\ • Right-click on an image.

*** ### Supernet Requirement **All Image Enhancement options run on the Sogni Supernet.**\ That means they require an active Supernet connection and consume **Spark Points**. * Spark cost is shown before you confirm an enhancement. * Cost varies based on factors like output resolution and the selected enhancement type. > Privacy note: Supernet processing is still privacy-respecting. Media is used only to run the job and deliver the result, then it’s automatically purged after a brief retention period. *** ### Creative Enhance Creative Enhance is meant for **bigger upgrades** and **creative refinement**. These enhancements can change details, styling, or rendering choices—especially at higher strengths—while still using your current image as the foundation. **Options:** * **Enhance with FLUX.1 \[schnell]** * **Enhance with Z-Image Turbo** #### Strength (Light / Mid / Heavy) Creative Enhance includes a **strength** control: * **Light**: subtle polish, safer changes * **Mid**: stronger refinement, more noticeable transformation * **Heavy**: maximum enhancement, can introduce larger creative shifts Use **Light** when you want the same image, just better.\ Use **Mid/Heavy** when you want to push style, detail, or “final look” more aggressively.

*** ### Generative Filters Generative Filters are “filters,” but they are **not traditional post-processing**. They use a **next-generation edit/mix model** to apply the chosen look while preserving: * **character identity** * **scene composition** * **overall consistency** This makes them ideal for applying structured changes (realism, tone, detail, restoration, etc.) without losing the subject. #### Categories Filters are organized into categories for discoverability: * **Realism** * **Fine Details** * **Focus** * **Blur** * **Color & Tone** * **Contrast** * **Noise** * **Resolution** * **Restoration** Each category contains multiple filter options. You don’t need to learn every filter—think of each category as a *family* of related transformations.

Image with "Boost Realism" filter applied

*** ### When to Use What Image Enhancement is especially useful when: * you like the composition, pose, or idea of an image, but it was generated with an **older model** * faces, hands, or fine details need repair * the image feels flat, synthetic, or under-realistic * you want to modernize an image without re-generating it from scratch This lets you “bring older images up to date” using newer models, while preserving the original intent and structure. **Use Creative Enhance when:** * you want a stronger upgrade or stylistic push * you’re okay with some creative change depending on strength * you want a “final pass” feel **Use Generative Filters when:** * you want targeted adjustments (tone, realism, detail, restoration, etc.) * you want to preserve character and scene consistency * you want controlled, repeatable edits *** ### Tips * If you’re happy with the composition, start with **Generative Filters** first. * If the image feels “almost there,” try **Creative Enhance (Light)** as a final pass. * If results drift too far, reduce strength or choose a more targeted filter category. --- # 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: ``` GET https://sogni.gitbook.io/sogni-docs/sogni-studio/creating-images/enhancing-images.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.