









None of the images in the previews were upscaled, detailed, or treated beyond adjusting the sampling steps.
This merge was created with the goal of achieving a pretty soft style.
I re-merged the model using different Loras and removing several models that was causing problems like deformations, noise and (imo) opaque colors. The watermark problem still persist due the Omega Pony is still part of the merge XD. I'm working in my own NAI style model, but is a work in progress.
I keep some of the previews propts for use as comparative.
It includes several models and Loras, such as
This model has a strong ???? bias due to the models used. Add the necessary negative prompts to avoid unwanted content.
Prompt:
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_upNegative Prompt:
source_pony, source_cartoon, source_furrySometimes it may be necessary to include "signature, logo" in your negatives due to the models used in the merge.
CFG Scale: 5
Sampling Steps: 20 - 30
Use these sizes for your generations to avoid deformations and loss of precision:
(1024, 1024),
(1152, 896),
(896, 1152),
(1216, 832),
(832, 1216),
(1344, 768),
(768, 1344),
(1536, 640),
(640, 1536)This model follows the same Pony V6 License.
1. 转载模型仅供学习与交流分享,其版权及最终解释权归原作者。
2. 模型原作者如需认领模型,请通过官方渠道联系海艺AI工作人员进行认证。我们致力于保护每一位创作者的权益。 点击去认领
