A curated list of Stable Diffusion Tips, Tricks, and Guides

Stable Diffusion:

• https://stable-diffusion-art.com/samplers

• https://civitai.com/articles/983/insights-for-intermediates-how-to-craft-the-images-you-want-with-a1111

• https://civitai.com/articles/904/settings-recommendations-for-novices-a-guide-for-understanding-the-settings-of-txt2img

• https://dataconomy.com/2023/08/28/img2img-stable-diffusion-image-to-image/

Video:

• https://civitai.com/articles/1841/guide-video2video

Tools/Utilities:

• https://searchcivitai.com

Training:

• Scripts / Tools

  • Kohya_SS [GitHub]

  • Dreambooth Extension for Stable-Diffusion-WebUI [GitHub]

• Information / How-To

  • Differences between training Methods: [YouTube video from koiboy]

  • Fine-tuning benchmark from Corridor Digital: [Link to Google Sheets]

  • Stable Diffusion Cheat-Sheet

LoRAs:

• Low-rank Adaptation for Fast Text-to-Image Diffusion Fine-tuning

• Understanding LoRA Training

  • Part 1 - Learning Rate Schedulers, Network Dimension and Alpha

  • Part 2 - Offset Noise, Epochs and Repeats

  • Part 3 - Block Weights

• Comparing LoRA Types in the Kohya_ss GUI

Textual Inversion:

• What is Textual Inversion?

Prompt Engineering:

• https://aituts.com/stable-diffusion-prompts

• https://prompthero.com/stable-diffusion-prompt-guide

• https://hackr.io/blog/stable-diffusion-prompts

• Prompting Juggernaut XL

Camera angles/position, Distance, and Lighting:

• Control Camera Angles In Stable Diffusion

• Mastering Camera Positions for AI Art and Generative AI

• Stable Diffusion enables the control of camera distance and angles

• Best Stable Diffusion Camera Prompts: Angles, Distance, Lens, and More

AI Image/Model Repositories (prompt ideas):

• https://civitai.com

• https://prompthero.com/ai-models

• https://tensor.art

• https://majinai.art

• https://holara.ai

Alternative UI to Automatic1111:

• Tools to Install multiple UIs

  • Stability Matrix

  • PInokio

• Manually Install UIs

  • SD.Next [GitHub]

  • Stable Diffusion Web UI-UX [GitHub]

  • InvokeAI [GitHub]

  • Fooocus [GitHub]

    • RuinedFooocus [GitHub]

  • ComfyUI [GitHub] [Beginner's Guide to ComfyUI]

    • StableSwarmUI [GitHub] (Beginner-friendly Interface to ComfyUI)

  • EasyDiffusion [GitHub]

Cloud-based alternatives to Stable Diffusion:

• Leonardo AI

• mage.space

• Playground

Live Image Generation:

• Krea

Academic Papers:

• Personalizing Text-to-Image Generation via Aesthetic Gradients [PDF]

• An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion [PDF]