PhotoGPT Advanced Settings for Image Generation

Pre-requisites before you dive into advanced settings

Before going through this guide, please ensure that you are familiar with the basic image generation and model training steps. If you want to revisit and freshen up your memory, kindly refer to the below guides for context:

• Introduction to PhotoGPT
• Selecting Ideal Input Images for Model Training
• Using presets for generating images
• Writing Effective Prompts for generating images
• Reference Image for Generation

Assuming you are confident in the basics, let's talk about some advanced options and how you can use them to get higer control over your generations and achieve even better results.

Advanced Settings and their Utility

There are two kinds of image generations possible within the PhotoGPT Dashboard:

• The first being character-based generation where you can select one of your trained models or a free character model from the model dropdown.
• The second one is the general purpose image generation for any use case. This kind does not require any training and can be used for a single click generation. These are specialized models like Nano Banana and Seedream that can be used for varied purpose.

Below we'll talk about the advanced settings available within both of these type of generations and how they can be used for achieving best suited results for your use case.

1. Character-based Generation

Go to your image generation dashboard, select a character model you want to work with from the model drop-down in the left pane and then click on "Advance Settings". This will open up some additional settings as shown in the below screenshots. Listed below are a short description of what each of these options are and how you can leverage them for achieving results suited better to your needs:

1. Steps: You can adjust this parameter to control how strongly the output image adheres to your text prompt. Increasing the number of steps (recommended 40-60) will increase prompt adherence while keeping it less than 30 will allow for more flexibility in your output. If you wish to have more varied results with the same prompts, it is suggested to keep the number of steps between 20-30 while if you have a detailed prompt that your output image should strongly adhere to, feel free to increase the number of steps upto 60-70 (recommended).
2. Seed: Use the same seed value to reproduce a composition or vary it to explore alternatives. You can check the seed of any image generated using PhotoGPT by simply opening the image dialogue box. Combined with the same prompt, preset and other settings, fixing the seed value can get you the exact same result.
3. Aspect Ratio & Resolution: Set aspect ratios that match your requirement. 1:1 for social avatars or posts, 3:4 for print and 9:16 for social media reels/shorts. The resolution of the ouput image is automatically adjusted to suit the selected aspect ratio.
4. Reference Image Style Strength: This option allows you to control how much the reference image influences the output image. Higher the value of this parameter, higher will be the influence of the image being used as input.
5. Enhance Face: This toggle simply allows you to get higher quality of facial features at the cost a few extra seconds during generation. While we ensure that you get optimal results in all your generations, in case you require even higher facial resemblance to the original character, you can check this box and then try generating the image.

Beyond these advanced settings, once you generate an image, you can use the image upscaler to get higher resolution or the AI Editor for a finishing touch.

2. General-purpose Generation

Within the same image generation page within your dashboard, you can select general purpose models from the model dropdown. Listed below are the general purpose image generation models currently available within PhotoGPT along with their respective advanced settings:

Here Safety Filter Level allows user to control sensitive content generation while Optimize Mode allows you to get faster generation with minimal quality loss.

In addition to these, the following options are available across all of these models and can be adjusted to suit your specific use case:

• Aspect Ratio: Each of these general purpose image generation models allow you to control the aspect ratio of the image regardless of the chosen resolution setting. You can toggle between classic 1:1 to a diverse range of 9:16 for shorts style, 21:9 for movie shot, etc.
• Sequential Mode: Checking this box during generation improves consistency across consecutive image generations.This mode can be used for things like story-boarding or simply getting the same shot from different angles.
• Seed: Similar to character-based generation, fixing the seed value allows you to reproduce the exact same scene. You can make minor tweaks in the settings or prompt to get variations of the same shot.

These settings come in handy for production quality shoots and allow for higher control over your creations. For more details or any questions related to a specific use case, feel free to hop into our Discord server and drop a message to our team.

Few Best Practices to keep in mind

• Refresh your model with new uploads every few month to keep styling current.
• Store successful/favorite generations in a separate folder in your library so your team can further build on them for future generations.

These additional options will provide you with higher control over the quality of your image as well as how your input influences your generated images.