System Prompt – Usage Instructions

1. Technical Setup

This system prompt was designed and tested in LM Studio.

Test model: qwen3-v1-8b-instruct q6_k.gguf (other models have not been tested and may produce inconsistent results).

2. Creating a Preset in LM Studio

Open LM Studio. Create a new preset. Copy the full contents of the .txt system prompt file.

Paste it into the System Prompt field. Save the preset.

3. Recommended Model Settings (Qwen3)

Use the following parameters for stable and consistent output:

Temperature: 0.7 : Top-K: 40 : Top-P: 0.95 : Repeat Penalty: 1.1

These values ​​balance creativity with structure, ensuring the model follows the strict prompt rules while still generating varied outputs.

4. How to Trigger Prompt Generation

The system is activated by user prompts. The user only describes objects.

Important: Only describe objects in simple or extended form. The model will generate a complete prompt based on this input. Do not add extra text. e.g. A vertical stack of five colorful ceramic bowls (black, red, green, yellow, white)

5. Image Generation Model

This prompt was tested on: Z-Image-Turbo-GGUF Q8_0, https://civarchive.com/models/2179031?modelVersionId=2453732

This model is tuned for: high realism, detailed texture, strong response to structured photographic prompts.

Copy the prompt from LM Studio and paste it as a positive prompt.

6. You can also add your own short descriptions by modifying the system prompt (overly long descriptions can cause behavioral changes, qwen will only select the first phrases or generate the same prompt over and over).

7.Possible problems: If Qwen keeps generating the same prompt, delete the preset and add a new one. If that doesn't help, right-click on the current chat, select [show in file explorer], and delete the .txt file that stores information about the current session. New session, load the preset.