I'm a photographer with hundreds of thousands of photos of beautiful models, can I use these to improve my Stable Diffusion?

• kohya-trainer

  36 1,772 8.3 Jupyter Notebook

  Discontinued Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning

I would recommend https://github.com/Linaqruf/kohya-trainer

• stable-diffusion

  2 69 10.0 Python

  Heavily refactored version of the stable diffusion development repository. Used for the SmirkingFace project. (by smirkingface)

All of the generalized models and larger projects use model trainers that are offshoots of Latent Diffusion, which is what Stable Diffusion used. I recommend this one, but there are many others. Some support auto-captioning, captioning tools, or you can caption the images yourself.

• InfluxDB

  www.influxdata.com featured

  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.

  

• stable-diffusion-aesthetic-gradients

  14 703 10.0 Jupyter Notebook

  Personalization for Stable Diffusion via Aesthetic Gradients 🎨

• stable-diffusion-webui-aesthetic-gradients

  10 420 10.0 Python

  Aesthetic gradients extension for web ui

• novelai-aspect-ratio-bucketing

  4 330 0.0 Python

  Implementation of aspect ratio bucketing for training generative image models as described in: https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac

  

Some more reading: https://github.com/NovelAI/novelai-aspect-ratio-bucketing

• SaaSHub

  www.saashub.com featured

  SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

  

Suggest a related project