Feel free to buy me a coffee ☕
--------------------------------------------------------------------------------
V2: It is not an improved version, it is a version trained with another model and in my opinion it is more malleable.
Note: Version 1 is more faithful to the anime animation.
--------------------------------------------------------------------------------
Trained: 85 images
--------------------------------------------------------------------------------
Recommendations:
Checkpoint: Below are the models that I personally recommend.
Weights: Values between 0.5 and 0.9 are considered decent, with the mid-point of 0.7 being the most appropriate in my opinion, although the choice depends on the individual and the type of image they wish to generate.
Vae: Anything-V4.0 (Opcional)
Sampler: DPM++ SDE Karras, 20 to 30 steps.
Sampler: DPM++ 2M Karras, 20 to 40 steps.
Hires.fix: R-ESRGAN 4x Anime6B , 0.5 denoising.
Negative prompt: This is an example of a general negative prompt that was used to generate the images.
" badhandv4, negative_hand-neg, verybadimagenegative_v1.3, ng_deepnegative_v1_75t (worst quality), (low quality), (normal quality), lowres,normal quality, ((monochrome)), ((grayscale)), ((watermark)),bad anatomy,bad hands, bad mouth, bad tongue, bad arms, extra arms, bad eyes, extra limbs "