Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

Image generation5 prompts

Stable Diffusion prompts that produce usable first drafts

An open image model family with unrivalled control through LoRAs, ControlNet and inpainting. Prompts pair weighted keywords with negative prompts and technical settings.

Local generationControlNet workflowsCharacter consistency with LoRAsInpainting and edits

What Stable Diffusion is good at

Stable Diffusion runs locally or on hosted GPUs and gives you control that closed models cannot match: ControlNet for pose and depth, inpainting for edits, LoRAs for consistent characters and styles, and schedulers that change the look. Prompting is only half the job; sampling steps, CFG scale, checkpoint and seed matter just as much. Write positive prompts as subject plus descriptors plus style plus quality terms, and keep a separate negative prompt for recurring defects. Do not overstuff; modern SDXL and SD3 models prefer cleaner prompts. Our Stable Diffusion prompts include recommended checkpoint families, CFG ranges and ControlNet pairings so results are reproducible.

Most-used Stable Diffusion prompts

See all →
Image Generation
Intermediate

Editorial portrait with soft window light

This copy-ready image prompt helps you editorial portrait with soft window light with fewer blank-page decisions. Paste it into Midjourney and Flux, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.

MidjourneyFluxStable Diffusion
4.7(23)1.4k copies

Minimal icon set

A image prompt for minimal icon set. It gives DALL-E and Leonardo a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.

DALL-ELeonardoStable Diffusion
4.7(53)1.1k copies

Character sheet for a game hero

A image prompt for character sheet for a game hero. It gives Leonardo and Midjourney a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.

LeonardoMidjourneyStable Diffusion
4.8(33)763 copies

Fantasy environment with scale

This copy-ready image prompt helps you fantasy environment with scale with fewer blank-page decisions. Paste it into Midjourney and Leonardo, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.

MidjourneyLeonardoStable Diffusion
4.9(34)724 copies

Watercolour botanical study

Watercolour botanical study with a prompt built for Midjourney and DALL-E. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.

MidjourneyDALL-EStable Diffusion
4.9(34)444 copies

How to write better Stable Diffusion prompts

These are the platform-specific habits our editors apply before publishing a template for Stable Diffusion.

  • 1

    Keep quality tags short on SDXL; use them mainly for SD 1.5 checkpoints.

  • 2

    Use a negative prompt for text, extra fingers and watermark artefacts.

  • 3

    Record checkpoint, sampler, steps and CFG with every saved prompt.

  • 4

    Use ControlNet when composition matters more than text description.

Verified Knowledge · FAQ

Stable Diffusion prompt FAQ

What this hub covers and how to get reliable output from Stable Diffusion.