Type | |
Stats | 951 |
Reviews | (142) |
Published | Jul 7, 2023 |
Base Model | |
Training | Steps: 30 |
Hash | AutoV2 E2D66C84A7 |
The model was developed based on the Copax Graceful model. However, this model produces brighter and more vibrant colors with good contrast.
You can observe certain similarities between the two models, but the development focus of this model is on creating vivid and vibrant colors, while for Copax Graceful, I intend to explore more complex color combinations.
+Version 2 improves eye details and enhances the liveliness of character expressions. There are slight changes in facial features and the overall appearance of the characters, along with subtle variations in the background blur effect.
Recommend:
step: 10 ~30
Denoising strength: 0.35
Sampler: DPM++ 2M Karras
Hires upscaler: 4x-UltraSharp or R-ESRGAN 4x+ Anime6B
N prompt:
illustration, 3d, 2d, painting, cartoons, sketch, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, vaginas in breasts, ((monochrome)), ((grayscale)), collapsed eyeshadow, multiple eyeblows, (cropped), oversaturated, extra limb, missing limbs, deformed hands, long neck, long body, imperfect, (bad hands), signature, watermark, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, bad image, bad photo