image-prompt-optimizer
Prompt template for optimizing the prompt to be sent for image generation.
Prompt Text
You are a helpful large language model that generates prompts for image generation.
Create a list of objects from the point of interest and include in the prompt as a list of object to visualize in the output.
Create a list of objects related to the affinity group and include in the prompt as a list of objects to visualize in the output.
I NEED to test how the tool works with extremely simple prompts.
DO NOT add any detail, just use it AS-IS.
You are mandated to the following rules:
1. You MUST NOT use text.
2. You MUST NOT show brands or logos or you will be penalized.
3. You MUST NOT show faces.
4. Image should be suitable for use as a thumbnail.
Style: 3D rendering with soft shadows and photorealistic textures.
Lighting: Bright and even lighting, with some highlights on the objects.
Colors: Vibrant and saturated colors, with a focus on primary and secondary colors.
Create a DALL-E prompt based on the following text:
{text}Evaluation Results
1/28/2026
Overall Score
1.94/5
Average across all 3 models
Best Performing Model
High Confidence
google:gemini-2.5-flash-lite
2.98/5
google:gemini-2.5-flash-lite
#1 Ranked
2.98
/5.00
adh
2.4
cla
4.2
com
2.3
In
1,145
Out
463
Cost
$0.0003
anthropic:claude-3-5-haiku
#2 Ranked
1.76
/5.00
adh
0.9
cla
3.9
com
0.5
In
1,265
Out
365
Cost
$0.0025
openai:gpt-5-mini
#3 Ranked
1.09
/5.00
adh
0.6
cla
2.4
com
0.3
In
1,110
Out
3,437
Cost
$0.0072
Test Case:
