Stable DiffusionBack to Prompts
Best Practices
Prompt Engineering for Stable Diffusion
Portkey.ai April 23, 2026
0 copies 0 likes
Covers the full prompt engineering workflow including subject specification, style references, quality boosters, camera and lighting terminology, negative prompt strategies, and CFG scale tuning for different prompt styles.
Prompt
Full Prompt Engineering Workflow: 1. **Subject Specification**: Clear, specific description of the main subject 2. **Style References**: Reference specific artists, art movements, or media types 3. **Quality Boosters**: masterpiece, award-winning, professional, ultra-detailed 4. **Camera Terms**: 50mm lens, shallow depth of field, macro, wide angle, telephoto 5. **Lighting Terminology**: Rembrandt lighting, split lighting, butterfly lighting, ambient occlusion 6. **Negative Prompt Strategy**: Start broad (low quality, blurry) then add specific fixes 7. **CFG Scale Tuning**: - Low (3-5): Creative, loose interpretation - Medium (7-9): Balanced quality and creativity - High (10-15): Strict prompt adherence, may reduce quality 8. **Sampling Steps**: 20-30 for most samplers, 50+ for DPM++ 2M Karras
How to Use
Follow the workflow from subject through CFG scale tuning. Adjust CFG scale based on how strictly you want the model to follow your prompt.
Comments
More Prompts
View allDevelopment
ComfyUI Advanced Workflow Designer
Design and optimize ComfyUI node workflows for Stable Diffusion. Covers ControlNet, IP-Adapter, inpainting, upscaling, and multi-pass generation pipelines.
C
CommunityCreative
SDXL Photorealistic Portrait Master
Generate stunning photorealistic portraits with SDXL. Covers lighting setups, camera simulation, skin texture, and professional photography techniques.
C
CommunityTechnical
A Guide to Prompt Engineering for Stable Diffusion
Technical deep-dive into prompt engineering covering token limits, attention mechanisms, prompt weighting with parentheses and numerical values, embedding manipulation, and A/B testing different prompt structures with reproducible experiments.
W
Weights & Biases (geekyrakshit)Negative Prompts
Negative Prompts for Stable Diffusion: The Complete Guide (2026)
Exhaustive guide to negative prompts covering common negative terms, negative embeddings (EasyNegative, bad_prompt), weighting strategies, model-specific negative prompts, and common mistakes like over-weighting.
I
ImageToPrompt.dev 1
Technical
Prompting & Prompt Weighting in Diffusers
Official Hugging Face documentation on prompt weighting techniques in the Diffusers library, covering Compel syntax, numerical weights, blend operations, and conjunction prompts for advanced control over generation.
H
Hugging FaceSDXL
Stable Diffusion XL Prompt Examples
Curated GitHub Gist with copy-paste SDXL prompt examples organized by category (portraits, landscapes, sci-fi, fantasy, product photography) with specific quality modifiers and style keywords tested on SDXL.
L
lukecav (GitHub)Ready-made automations for this
Workflows from the Neura Market marketplace related to this Stable Diffusion resource
- Process Invoices & Engineering Emails with Gmail, AI Analysis & Telegram Alertsn8n · $14.99 · Related topic
- AI-Generated LinkedIn Posts with OpenAI, Google Sheets, & Email Approval Workflown8n · $14.99 · Related topic
- Automated Sonarr Missing Episode Finder with Quality & Language Filteringn8n · $9.99 · Related topic
- Automate AI-Driven Engineering Department with OpenAI Agentsn8n · $14.99 · Related topic