RedRayz's picture
Update README.md
efa0eb2 verified
|
raw
history blame
1.55 kB
metadata
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
pipeline_tag: text-to-image
base_model:
  - Laxhar/noobai-XL-Vpred-1.0
tags:
  - stable-diffusion
  - stable-diffusion-xl

Abydos_Noob_v-pred-1.1.0

Modified NoobAI-XL(v-prediction) with Blue Archive style

Civitai model page

About 1.1.0

Improved stability Better shadow rendering?

Recommended Prompt

official art, blue archive, game cg, non-web source, newest

Recommended Negative Prompt

lowres, oldest

Recommended Settings

Steps: 14-24

Sampler: DPM++ 2M SDE, DPM++ 3M SDE or Euler a

Scheduler: Simple or SGM Uniform

Guidance Scale: 2-5

Hires.fix

Upscaler: 4x-UltraSharp or Latent(nearest-exact)

Denoising strength: 0.4(0.6-0.7 for latent)

Training steps

  1. Make 2 models from NoobAI-XL v-pred 1.0(=A,B), A with ZTSNR, B w/o ZTSNR
  2. Merge A and B MBW(0,0,0,0,0,0.3,0.3,0,0.5,0.5,0.5,0.5,0.5,0.5,0.3,0.3,0,0,0,0) Adjust(0,0,0,0,-0.1,0,0,0)=tmp1
  3. tmp1 + spo_sdxl_10ep_4k-data_lora_webui x 1 + sdxl-boldline x -0.5 = Result

Training scripts:

sd-scripts

Notice

This model is licensed under Fair AI Public License 1.0-SD

If you make modify this model, you must share both your changes and the original license.

You are prohibited from monetizing any close-sourced fine-tuned / merged model, which disallows the public from accessing the model's source code / weights and its usages.