> ## Documentation Index
> Fetch the complete documentation index at: https://support.myapps.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Image FAQ

> Common questions about generating and editing images in Pixio

## Choosing a model

<AccordionGroup>
  <Accordion title="Which image model should I start with?">
    [Flux](/families/flux) — the widest range in Pixio, strong prompt adherence, and the best LoRA support. Compare against [Stable Diffusion](/families/stable-diffusion) and [OpenAI](/families/openai) on the same prompt before settling.
  </Accordion>

  <Accordion title="I need text inside the image">
    Try [Ideogram](/families/ideogram) — it's the family best known for legible text in images.
  </Accordion>

  <Accordion title="I need a logo or something that scales">
    You want vector output, not a raster image. [Recraft](/families/recraft) is the main source of SVG output in Pixio.
  </Accordion>

  <Accordion title="I want to edit an existing image, not make a new one">
    Filter for **image-to-image** or **inpainting**. [Qwen](/families/qwen), [Reve](/families/reve), and [Flux](/families/flux) all lean editing. For a change described in words, the Edit Image action from [Grok](/families/grok) works well.
  </Accordion>

  <Accordion title="Why do two models with the same capability behave so differently?">
    Same capability doesn't mean same controls. Two text-to-image models can accept completely different inputs. Check the tooltips on each input in [Generate](/generate) rather than assuming a setting exists.
  </Accordion>
</AccordionGroup>

## Quality and prompts

<AccordionGroup>
  <Accordion title="My results don't match my prompt">
    Usually the model, not the prompt. Prompt adherence varies a lot between families — try the same prompt on a [Flux](/families/flux) model before rewriting it. If one model consistently ignores you, it's the wrong model for that job.
  </Accordion>

  <Accordion title="How do I get consistent results across images?">
    Fix the **seed** if the model exposes one — same seed and same prompt gives you a repeatable starting point. For a consistent subject or character across many images, train a [LoRA](/advanced/model-training).
  </Accordion>

  <Accordion title="Can I get a specific person or product to look right every time?">
    That's what LoRA training is for. Train on 15–30 varied images of the subject, then trigger it with its trigger word. See [Model Training](/advanced/model-training).
  </Accordion>

  <Accordion title="The image is right but too small or soft">
    Don't regenerate — upscale. Use the **Upscale** or **Image Upscale** [chained action](/generate#chained-actions), or [Magnific](/families/magnific) directly.
  </Accordion>
</AccordionGroup>

## Costs

<AccordionGroup>
  <Accordion title="How much does an image cost?">
    Depends on the model — from a couple of credits up to a few dozen. The cost is shown in the picker and again before you submit. See [Credits & Plans](/credits).
  </Accordion>

  <Accordion title="How do I not waste credits?">
    Draft on a cheap model at low resolution to get composition and prompt right, then rerun the keeper on a better model. Iterating on the expensive model is the most common way people burn a balance.
  </Accordion>

  <Accordion title="I was charged for an image I don't like">
    Successful generations cost credits even if the output isn't what you wanted. Only **failed** runs are free. That's the reason to test cheap first.
  </Accordion>
</AccordionGroup>

## Inputs and outputs

<AccordionGroup>
  <Accordion title="How do I use my own image as a reference?">
    Upload it in the generation form, or pick an existing file from your assets. Uploads are reusable — they land in the Uploads tab of [My Assets](/assets).
  </Accordion>

  <Accordion title="Where did my image go?">
    [My Assets](/assets) → Generated, and in the history column in [Generate](/generate). The prompt is in [Prompt History](/library/prompt-history).
  </Accordion>

  <Accordion title="Can I remove the background?">
    Yes — the **Remove BG** chained action, or a background-removal model in [3D & utility](/families/3d-and-utility).
  </Accordion>
</AccordionGroup>

## Related

* [Models](/models) — how to navigate the catalog
* [Generate](/generate) — the studio in detail
* [Academy](/academy) — model-specific lessons