Image Generator

Usage

Ensure you have installed the required dependencies (pip install openai). Use the bundled script to generate images.

Qwen-Image (Default)
CODEBLOCK0

Kolors
CODEBLOCK1

GLM-Image
CODEBLOCK2

HunyuanDiT-v1.2-Diffusers-Distilled
CODEBLOCK3

FLUX.2-dev
CODEBLOCK4

Options

• - 256x256 - Small square format
• INLINECODE2 - Square format
• INLINECODE3(default) - Square format
• INLINECODE4 - 16:9 landscape
• INLINECODE5 - 9:16 portrait
• INLINECODE6 - 4:3 format
• INLINECODE7 - 3:4 portrait
• INLINECODE8 - 16:10 landscape
• INLINECODE9 - 10:16 portrait
• INLINECODE10 - High-resolution square format

Additional flags:

• - --model - Specify the model to use. Options include Qwen-Image (default), Kolors, GLM-Image, FLUX.2-dev, HunyuanDiT-v1.2-Diffusers-Distilled.
• INLINECODE17 - Specify what elements users want to avoid in the generated image(default: "低分辨率，低画质，肢体畸形，手指畸形，画面过饱和，蜡像感，人脸无细节，过度光滑，画面具有AI感。构图混乱。文字模糊，扭曲。").
• INLINECODE18 - Specify the size of the generated image. Options include 256x256, 512x512, 1024x1024 (default), 1024x576, 576x1024, 1024x768, 768x1024, 1024x640, 640x1024, 2048x2048.
• INLINECODE29 - Float value to control how closely the model adheres to the prompt (default depends on model).
• INLINECODE30 - Integer for denoise steps (default depends on model). Higher values typically increase quality but take longer.

Model Specific Defaults:

• - Kolors: steps 25 (range 20-30), scale 7.5 (range 0-100)
• INLINECODE32: steps 30 (range 4-50)
• INLINECODE33: steps 30 (range 10-50), scale 1.5 (range 0-10)
• INLINECODE34: steps 25 (range 25-50), scale 5 (range 0-20)
• INLINECODE35: steps 20 (range 10-50), scale 7.5 (range 0-100)

Workflow

1. 1. Execute the performimagegen.py script with the parameters from the user.
2. Parse the script output and find the line starting with IMAGE_URL:.
3. Extract the image URL from that line (format: IMAGE_URL: https://...).
4. Display the image to the user using markdown syntax: 🖼️[Generated Image](URL).

Notes

• - You should not only return the image URL but also describe the image based on the user's prompt, and claim the hyperparameters used for generation.
• You should always wait for the script to finish executing, don't shut it down prematurely.
• The Lanaguage of your answer should be consistent with the user's question.
• By default, return image URL directly without downloading.
• If GITEEAIAPIKEY is none, the user must provide --api-key argument.
• The script prints IMAGE_URL: in the output - extract this URL and display it using markdown image syntax: 🖼️[Generated image](URL).
• Always look for the line starting with IMAGE_URL: in the script output and render the image for the user.
• You should honestly repeat the description of the image from user without any additional imaginations.
• Handling User Feedback on Quality: If the user states the image quality is low or lacks details, you should retry generating with a higher --num-inference-steps (e.g. 25 → 30).
• Handling User Feedback on Prompt Adherence: If the user states the image doesn't follow the prompt closely enough or ignores details, increase the --guidance-scale parameter (e.g. 7.5 → 15). If they say it's oversaturated or distorted, decrease it.