- Prompt at a glance
- Category
- Image
- Works with
- Stable Diffusion
- Length
- 72 words
- Fields to fill
- SUBJECT, SETTING
- Last updated
Realistic portrait photo
This Stable Diffusion prompt describes a candid portrait in soft window light with an 85mm look. It comes with a negative prompt against plastic skin and bad hands, and the size, steps and CFG to start from.
Photo of [SUBJECT, e.g. a woman in her 30s with short curly hair] in [SETTING, e.g. a sunlit cafe by the window], looking slightly off camera, natural soft window light, 85mm lens, shallow depth of field, natural skin texture, warm muted colours, candid editorial photography. Negative prompt: cartoon, illustration, 3d render, plastic skin, extra fingers, deformed hands, blurry face, watermark, text Settings: 1024x1280 (SDXL) or 896x1152 (SD 3.5), 30 steps, CFG 5-6
Use a photo-focused checkpoint and keep the CFG low for natural skin. High CFG makes faces look waxy.
From copy to picture in four steps
- 1
Open Stable Diffusion and start a new image.
- 2
Paste the prompt and replace the [BRACKETED] fields with your subject or brand.
- 3
Generate a few variations and pick the closest.
- 4
Refine by changing one detail at a time, such as the lighting, angle or colours.
About this prompt
Which AI tools work with this prompt?
It is written for Stable Diffusion. Paste it into your preferred tool and adjust the wording if the result is off.
What do I need to fill in?
Replace these fields before you send it: SUBJECT, SETTING. Each field shows an example in the prompt.
Can I use the generated image commercially?
That depends on the tool you generate it with and your plan. Check that tool's terms before you publish or sell the result.
