About: "𝑹𝑬𝑨𝑳 𝘔𝘐𝘕𝘛⋆"... this is a meticulously crafted experimental model, consisting of merging of a large number of existing checkpoints - some well known and some very obscure - as well as custom trained LoRAs, that which aims to provide:
Realism, particularly in human subjects.
A subtle human imperfection not found in a lot of models.
Flexibility in adapting to most LoRAs.
High dynamic range for preservation of details.
An interesting uniqueness in its choices.
Consistency in its particular abilities.
(NOTE: 𝑹𝑬𝑨𝑳 𝘔𝘐𝘕𝘛⋆ is not beginner friendly!)
Recommended settings:
Sampling:
Most methods seem to work well, with DPM++ 3M SDE Exponential (35+ steps) being a personal favorite.
CFG: 3-6 (Dynamic Thresholding highly recommended for higher values)
Steps: Surprisingly good results have been observed with as few as 10 steps.
VAE: Baked in. (difConsistency RAW)
The model will be an ongoing work in progress.
Your review and feedback means a lot! ❤️
per Civitai user 'Tiler_Blurden' (link here: https://civitai.com/models/294100/real-mint?modelVersionId=330526)
