[Merge] SemiRealistic ((Yesmixv15=35%+Photon=65%))版本v1.0 (ID: 160101)

I hope y'all are enjoying this first model merge. I knew the moment I saw the shear quality and consistency from h_madoka's character lora's. This was going to be my first attempt, given how forgiving this merge was. I would say it turned out better than expected.

Update:

Might update sample image with newly obtained knowledge from more recent model merge.

All images are 512x768, made in Draw Things.

Works well with loras from https://civitai.com/user/h_madoka

Example prompt for Android 21:Android 21 人造人間21号 /Dragon Ball FigtherZ - v1.0 | Stable Diffusion LoRA | Civitai

masterpiece, best quality, highres, aaandro, brown hair, long hair, curly hair, blue eyes, hoop earrings, two-tone dress, checkered dress, sleeveless, black pantyhose, dragon ball, <lora:android_21_v1:0.7>, street, cowboy shot, standing, smile, <lora:skinny_new_skin:0.2> <lora:detailed_eye:0.1> RAW photo, a young woman (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3

Loras, Embeddings and Models used:

[Loras]

videl_v10:Videl ビーデル /Dragon Ball Z - v1.0 | Stable Diffusion LoRA | Civitai

android_21_v1:Android 21 人造人間21号 /Dragon Ball FigtherZ - v1.0 | Stable Diffusion LoRA | Civitai

skinny_new_skin:Skin & Hands (male/female) from Polyhedron - v1.1 | Stable Diffusion LoRA | Civitai

detailed_eye:https://huggingface.co/casque/detailed_eye-10/tree/main

[Embeddings]

https://civitai.com/models/72437/baddream-unrealisticdream-negative-embeddings

EasyNegative - EasyNegative | Stable Diffusion Embedding | Civitai

[Models]

Photon - v1 | Stable Diffusion Checkpoint | Civitai

【Checkpoint】YesMix - v1.5 | Stable Diffusion Checkpoint | Civitai

描述:

训练词语: