Type | |
Stats | 2,183 |
Reviews | (360) |
Published | May 10, 2023 |
Base Model | |
Hash | AutoV2 88C5C6FDD3 |
Want me to create custom models for you? please visit my Fiverr page:
https://www.fiverr.com/s/Xar15Pv
It's not necessary but If you like my creations please consider to support me to create more projects by donate in here:
https://ko-fi.com/gorillamonsooniii
https://www.patreon.com/GorillaMonsoon
Solstice
Solstice is my attempt to create Manhwa (korean webtoon) artsyle model. Different from the usual manga art style used in some of the models trained in stable diffusion.
Legal & Risk
In principle, I do not support the use of this model to generate any adult content. When using this model, users must abide by laws and regulations, and do not infringe other people's reputation, privacy or portrait rights.
Changelogs
v1.0-Areum: First release, "forking" my Eclipse checkpoint, reworked most of it's datasets to Manhwa artstyle.
v1.0-Areum: added safetensors format, eveything is same as ckpt format, just in safetensors format
v1.0-Areum-NoEMA-fp16: added Pruned, No EMA, fp16 version. need download my GMIII VAE, you can use any other VAE, but the result may vary.
Who find this model perfect
LoRA/LoCon/LyCORIS user who are looking for a compatible checkpoint
Creative prompters
People who needs Manhwa model
Usage
Almost compatible with all sampling methods available, but Euler a and DPM++ SDE Karras are my recommendation
Use 20-40 sampling steps, more than 40 is not giving any improvement
CFG: 4.5-7
Less complicated, short negative prompts are better
This model include VAE, so please use with it.
If using Hires:
Hires step: 10-20 steps
R-ESRGAN 4x+ Anime6b, if you're prefer Latent upscaler, use Latent (nearest-exact)
After download this model, try to share with us about your findings.
Please give star reviews with your generated picture if you like it.
I'm also accept commisioning for LoRA/Ckpt