Open Prompts is the dataset used to build krea.ai. The data comes from the Stability AI Discord and includes around 10M images from 2M prompts. You can use it for creating semantic search engines of prompts, training LLMs, fine-tuning image-to-text models like BLIP, or extracting insights from the data—like the most common combinations of modifiers.
Design and optimize ComfyUI node workflows for Stable Diffusion. Covers ControlNet, IP-Adapter, inpainting, upscaling, and multi-pass generation pipelines.
Generate stunning photorealistic portraits with SDXL. Covers lighting setups, camera simulation, skin texture, and professional photography techniques.
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.
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.
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.
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.
Workflows from the Neura Market marketplace related to this Stable Diffusion resource