-
sd-dynamic-thresholding
Dynamic Thresholding (CFG Scale Fix) for Stable Diffusion (StableSwarmUI, ComfyUI, and Auto WebUI)
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
sd-dynamic-prompts
A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
Use sd-dynamic-thresholding extension (set CFG scale to 12 or more and mimic CFG scale to 7): https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
Use adetailer extension to automatically inpaint face: https://github.com/Bing-su/adetailer
From (https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/5674) --
Then with the result, I use the Dynamic Prompts Extension to chain them all together like this to give wildly different backgrounds to every image.
you can try realistic models like majicmix (civitai.com) under stable diffusion, you can also combine multiple realistic models (merge), in the site you will find images with the prompts that you can copy and test out, negative prompts are very important in those realistic generations so download some textual inversion embeddings (like BadDream etc), Adetailer extension is also a good help for face details, badhandV4 embedding is good for hands etc....you can also add some loras for details (addetails lora) , (noiseoffset), and some upscaling :)