Description
RealMythXL-Myth
V5.5 Super Edition-Member Exclusive
.
V5.5 is a refined version of V5 Super (some image performance of V5.5 still needs testing) Recommend using high-resolution repair and ADetailer for local repair
(V6 version has completed preliminary training and awaits refined testing)
The RealMythXL model currently has a regular version (lite unrefined version, available for download for trial play from time to time) and a Lib member version (refined version)
.
New quality words added adamcn myth style (Adam's style) and wukong and some other mythical characters awaiting updates
Training difficulty for Chinese mythology concepts is relatively high welcome to submit related materials
.
Enhancements of national style mythological elements were made in the V5.5 version, with detail texture enhancement ahead of the MJ level
Based on the v5 version, adjustments and fusion were made, using movie-level data upgrades and attempting upgrades and enhancements to architectural structures
Improved portrait details, increased image output rate targeted training for traditional ancient costume elements and Chinese mythological concepts performs well on science fiction elements
.
Example images are from the forge or A1111 version of webui output, both can directly replicate
Reference parameters Steps: 30, Sampler: Restart, Size: 768x1152,
CFG 1~5
Supporting common quality words to enhance image quality
Recommended hint words can be seen in the example images, welcome everyone to actively provide feedback and comments
.
Model usage statement: Commercial use without authorization is prohibited Model feedback exchange group q 765120433
1. You shall not host this model and its derivative versions (such as blended model versions) on websites/applications intended to earn revenue or donations.
2. You shall not intentionally use this model to produce or share illegal or harmful content for dissemination and output. Please abide by public morality, and use this model for positive and constructive purposes. The model production is not easy, so if you use a fusion of this model, it is recommended to indicate the original model to avoid unnecessary misunderstandings. Thank you
