> For the complete documentation index, see [llms.txt](https://help.arcanalabs.ai/learning-center/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.arcanalabs.ai/learning-center/demos-and-tutorials/paintbrush-for-fixing-an-image.md). # Paintbrush for fixing an image Paintbrush is the most powerful way to make precision inpaints that quickly get the results you need.

## STEPS OVERVIEW OF STEPS: 1. using dropper to match the environment's colors, crudely recolor the space to conceptualize the fix 2. mask over it 3. prompt the change you want to see 4. work from 30-66% transformation 5. Use MJ XL model for best results using paintbrush 6. Send improved results to source to repeat any process until refined\ \
STEP 1: Using dropper to match the environments colors, crudely recolor the space to conceptualize the fix

Using dropper to get the shirt color correct

See how we quickly paint to blend into environment.

\ STEP 2: mask over it

Use Mask brush to Mask over the painted area and allow a bit of the unpainted space to be masked as well so it blends better. The masked area is the area you are telling Arcana you want to transform

\ **STEPS 3-5:** Prompting, Model Selection, Transformation levels set * **prompt the change you want to see:** *woman wearing red tanktop tank top, counter with piece of paper* * **work anywhere within the range of 30-66% Transformation:** We went with 45%. This means transform 45% of the image to something new. In other words, preserve 55% of the original. In our case, this is preserving the colors of our paintbrush. * *Use MJ XL model* for best results using this paintbrush technique.

Result

Prompt used: *woman wearing red tanktop tank top, counter with piece of paper*
Model: MJXL
Transformation: 45%

\ \ \ **BONUS STEP - CHANGING FACE**\ \ \

We masked over the face. Selected a model. And wrote the change we wanted to see. In this case we wanted "Freckled girl"

CHANGES MADE TO FACE USING SAME PROMPT, JUST DIFFERENT MODELS:

--- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://help.arcanalabs.ai/learning-center/demos-and-tutorials/paintbrush-for-fixing-an-image.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.