> 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/introduction/conjure-tools/skeleton.md).
# Skeleton
Use a reference image to predetermine the posture of your conjured image.
One reference image of a pose you like. Endless possibilities.
## STEP 1 - Upload reference image
You can either upload an image made inside Arcana or upload from your computer.
## STEP 2 - Determine level of influence
The influence slider determines how strictly you want the new conjured image to obey the skeletal reference. Increasing past 1 may be necessary at times but rely on default at first. Decreasing below 1 will incrementally reduce the influence of your reference image on the final image but may improve the quality of output.
NOTE: If you like the image output but feel it needs better details, DON'T RE-CONJURE, just send it to the TRANSFORM SUITE where you can inPaint to further refine the details. Once pleased, then send your image to the [ENHANCE SUITE](/learning-center/introduction/suite-overview/enhance-suite.md) to produce stunning additional details at 2x resolution.
## STEP 2b (optional) - Click Preprocess
This allows you to test and assure that Arcana has properly scanned the uploaded reference image and extracted its skeleton correctly.
## STEP 3 - Select Model & Output Size
MJ XL is our favorite model but do not discount the other XL models as they each have their own unique strengths and weaknesses. \
\
Ideally, your reference image should be the same size as your output image, but this is not required.
If you have a very specific output size in mind, select advanced tab and set a customized output size for your conjured image.
## STEP 4 - Prompt ANYTHING.
Just write what you want the image to be and watch the magic happen!
NOTE: If you like the image output but feel it needs better details in the face or clothes or environment, DON'T RE-CONJURE, just send it to the TRANSFORM SUITE where you can inPaint to further refine the details. Once pleased, then send your image to the [ENHANCE SUITE](/learning-center/introduction/suite-overview/enhance-suite.md) to produce stunning additional details at 2x resolution.
## TUTORIAL VIDEO
{% embed url="" %}
---
# 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/introduction/conjure-tools/skeleton.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.
