Description:

A merge model of those models; catTower v1.5(vpred), cyber realistic xl v4, itercomp v1 and movable figure model illustrious xl v1. This model require V-pred supported client; like as a1111dev, forge, reforge, comfyui.

The recipe is included in sample images.

Entry settings:

Euler: 24 steps, CFG: 5
PP: masterpiece, newest,

NP: worst quality, comic, multiple views, bad quality, low quality, lowres, displeasing, very displeasing, bad anatomy, bad hands, scan artifacts, monochrome, greyscale, twitter username, jpeg artifacts, 2koma, 4koma, guro, extra digits, fewer digits, jaggy lines, unclear, oldest

If you want more NP effect or vividness, increase Steps and CFG. up to around 7, there are few side effects.

Note:

To set the model type as V-pred automatically, After model export, the keys "v_pred" and "ztsnr" were written into the state_dict of the model using this python function.

import torch

from safetensors import safe_open

from safetensors.torch import save_file

def append_vpred_keys(input_filename, output_filename):

    with safe_open(input_filename, framework="pt", device="cpu") as f:

        state_dict = {key: f.get_tensor(key) for key in f.keys()}

    state_dict["v_pred"] = torch.tensor([0])

    state_dict["ztsnr"] = torch.tensor([0])

    save_file(state_dict, output_filename)