Type | |
Stats | 771 |
Reviews | (91) |
Published | Oct 26, 2024 |
Base Model | |
Training | Steps: 5,000,000 Epochs: 10 |
Hash | AutoV2 9FF0E8FCFA |
MeinaXL objective is to be able to do good art with little prompting. ( this is still in progress tho )
I have a discord where you can share images, discuss prompt and ask for help. https://discord.gg/meinaverse
我有个可以让你分享图片和参与讨论与询问问题的discord群。
I also have a ko-fi and Patreon page where you can support me or buy me a coffee <3 , it will be very much appreciated:
https://ko-fi.com/meina and https://www.patreon.com/MeinaMix
MeinaXL and the other of Meinas will ALWAYS be FREE.
It was trained on top of AstreaPixie XL Anime by AstreaPixie
Cover image lora made by: FallenIncursio | Civitai
Recommendations of use:
--------------------------------------------------------------------------------
Enable Quantization in K samplers.
Hires.fix is needed for prompts where the character is far away in order to make decent images, it drastically improve the quality of face and eyes!
---------------------------------------------
Recommended parameters:
Sampler: DPM++ SDE Karras: 20 to 25 steps.
Sampler: DPM++ 2M Karras: 25 to 60 steps.
CFG Scale: 4 to 7.
Resolutions: 1024x1280, 832x1280 for Portrait!
Resolutions: 1536x1024 ( or higher ) for Landscape!
Hires.fix: R-ESRGAN 4x+Anime6b, with 10 steps at 0.3 up to 0.5 denoising.
Clip Skip: 2.
Negatives: ' interlocked fingers, sketch, 3d, loli, nude '
--------------------------------------------------------------------------------