license: creativeml-openrail-m
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- art
- anime
- stable diffusion
- openvino
- onnx
SoteMix V2 is trained at 1024x1536 for high resolution image generations.
This model is tested on SD.Next with Diffusers backend and HyperTile size 384.
Positive Prompts:
masterpiece, best quality, highres, 1girl,
Negative Prompts:
(worst quality, low quality, lowres), zombie, interlocked fingers,
Do not use any negative embeddings.
Sampler: Euler a
Steps: 30-40
Clip Skip: 1
CFG: 4-7
Base Resolution: 512x
/ 768x
/ 1024x
/ 768x1280
/ 960x1280
/ 1024x1536
/ 1920x1080
Model can still be chaotic at 1024x1536
and 1920x1080
.
Second Pass / Hires:
Sampler: Euler
/ Euler a
Steps: 10
with Euler
/ 20
with Euler a
Upscaler: RealESRGAN 4x+ Anime6B
/ ESRGAN 4x-AnimeSharp
with 0.2
-0.3
denoise strength.
CFG: 6-9
Resolution: 2x
of the base resolution.
Training:
My GPU couldn't handle full model training at these resolutions so i trained it as a 512
layer Lora with SoteMix V1 as the base.
Used highres as the trigger word. Also used raifu trigger word with my OC character.
Resolution: 1024x1536 with Bucketing
Batch Size: 1
Steps: 20000
GPU: Intel ARC A770 16GB
Bucket:
bucket 0: resolution (832, 1664), count: 49
bucket 1: resolution (896, 1280), count: 1
bucket 2: resolution (896, 1536), count: 2
bucket 3: resolution (960, 1536), count: 12
bucket 4: resolution (960, 1600), count: 531
bucket 5: resolution (1024, 1344), count: 209
bucket 6: resolution (1024, 1408), count: 31
bucket 7: resolution (1024, 1472), count: 1
bucket 8: resolution (1024, 1536), count: 847
bucket 9: resolution (1152, 1344), count: 6
bucket 10: resolution (1216, 1216), count: 34
bucket 11: resolution (1344, 1024), count: 17
bucket 12: resolution (1344, 1152), count: 2
bucket 13: resolution (1536, 896), count: 92
bucket 14: resolution (1536, 1024), count: 34
bucket 15: resolution (1600, 960), count: 187
bucket 16: resolution (1664, 832), count: 21
bucket 17: resolution (2048, 768), count: 3
bucket 18: resolution (2304, 576), count: 1
Merge:
Merged SoteMix V1 with Lunar Radiance Light and then merged the Hires Lora i trained on top of it.
Merge ratio: (0.6 SoteMix V1 + 0.4 Lunar Radiance Light) + 0.7 Hires Lora