> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aistudio.youthnic.shop/llms.txt
> Use this file to discover all available pages before exploring further.

# Configure Output and Model Settings for Your Photoshoot

> Set the generation model, aspect ratio, resolution, quality level, model identity, background style, and Pose QA before starting your photoshoot.

Open the **Output settings** panel in Studio to configure how your photoshoot is generated. All settings are locked into the generation session the moment you click **Generate** — changing any setting after generation starts has no effect on the active job.

The panel header shows a live summary of the current configuration: `gpt-image-2 · 3:4 · 2K · medium quality`.

## Generation model

<ParamField body="model" type="select" default="gpt-image-2">
  The AI model used to generate all five pose images.

  * **GPT Image 2** (`gpt-image-2`) — default model, optimized for photorealistic fashion imagery following OpenAI's virtual clothing try-on guidance
  * **Reve 2.1 Image** (`reve-2.1-image`) — alternative model for experimentation
</ParamField>

## Aspect ratio

<ParamField body="aspectRatio" type="select" default="3:4">
  Controls the output image dimensions. Choose based on your primary publishing destination.
</ParamField>

| Ratio | Dimensions    | Recommended use                                   |
| ----- | ------------- | ------------------------------------------------- |
| 3:4   | Portrait      | Flipkart, Myntra, Amazon product images (default) |
| 4:5   | Portrait      | Instagram feed posts                              |
| 2:3   | Tall portrait | Full-length editorial frames                      |
| 9:16  | Vertical      | Instagram Reels, TikTok, Stories                  |
| 1:1   | Square        | Marketplace thumbnails, WhatsApp catalog          |

<Tip>
  If you publish to multiple channels, generate at 3:4 for marketplaces first, then re-run at 9:16 for social. The consistency anchor from Pose 1 keeps the model and scene identical across both runs.
</Tip>

## Resolution

<ParamField body="imageSize" type="select" default="2K">
  Output resolution.

  * **2K** — high-resolution output suitable for marketplace listings and print
  * **1K** — lower resolution for quick drafts and internal review
</ParamField>

## Generation quality

<ParamField body="quality" type="select" default="medium">
  Controls the level of detail, generation time, and cost per image.

  * **Low** — fastest draft quality, lowest cost; use for rapid iteration
  * **Medium** — balanced default; suitable for most catalog and marketplace requirements
  * **High** — maximum detail and accuracy; highest cost; use for hero images or premium campaigns
</ParamField>

Medium is the default and the right choice for most catalog runs.

## Model identity

<ParamField body="modelIdentity" type="select" default="Same adult South Asian female fashion model across every pose">
  Describes the model used for every pose in the session. All five frames are generated to match this identity.

  | Option                 | Description                                                   |
  | ---------------------- | ------------------------------------------------------------- |
  | South Asian — Female   | Same adult South Asian female fashion model across every pose |
  | Asian — Female         | Same adult Asian female fashion model across every pose       |
  | Auto selected — Female | Same adult female fashion model selected to suit the garment  |
  | Auto selected — Male   | Same adult male fashion model selected to suit the garment    |

  To lock a specific face rather than an ethnicity description, upload a **Model face lock** image in the Product references section.
</ParamField>

<Note>
  Changing model identity marks the current analysis stale and triggers an automatic re-analysis before generation can start, because the model description is part of how Gemini plans the shoot.
</Note>

## Background style

<ParamField body="backgroundStyle" type="select" default="Infer a premium consistent scene from the uploaded style reference">
  Determines the backdrop, environment, and lighting direction used across all five poses.

  | Option               | Effect                                                       |
  | -------------------- | ------------------------------------------------------------ |
  | Auto from references | Infers a premium scene from your uploaded style references   |
  | Studio grey          | Minimal warm-grey fashion studio with soft directional light |
  | Studio white         | Clean seamless white e-commerce studio with soft shadows     |
  | Outdoor editorial    | Premium outdoor scene with natural golden-hour lighting      |

  You can also type a custom scene description directly in the **Scene direction** field in the Analysis & Pose Plan panel after analysis runs.
</ParamField>

<Note>
  Changing background style marks the current analysis stale — Gemini re-analyzes with the new scene direction before generation can start.
</Note>

## Pose QA

<ParamField body="poseQa" type="boolean" default="false">
  When enabled, Gemini runs a consistency validation check on every generated pose image before it is marked complete. QA checks the generated image against the Product Identity Profile and the approved consistency anchor.

  * **Enabled** — each pose goes through an extra Gemini QA pass; poses that fail are automatically retried with a minimum 30-second backoff
  * **Disabled** — poses are delivered without automatic validation; QA status is shown as "Unverified" in History
</ParamField>

Pose QA adds time per pose. Enable it for final production runs where garment accuracy is critical. Leave it off for rapid drafts or internal review rounds.

## Styling plan editor

After analysis completes and the result is current, the **Footwear, jewellery & styling** panel appears below the Output settings. Gemini proposes a specific footwear, jewellery, and accessory plan based on your product photos and style references.

<Tip>
  Edit the styling plan before you generate — these exact pieces are locked into all five frames. The styling plan is saved independently of the product analysis, so editing it does not mark the analysis stale or trigger a re-analysis.
</Tip>

The styling plan includes:

* Footwear style and color
* Necklace, earrings, bangles, and ring descriptions
* Handbag or clutch
* Additional accessories (dupatta, belt, hair accessories)
* Nail color

Click **Save for this shoot** to persist your edits before generating.