V3
Z-image is pretty good.Basically, it can run with or without trigger words. My dataset tags include trigger words, but I feel it can still achieve good results without them. Using natural language prompts would be better, but word prompts are also acceptable.
The prompts can be generated using the system prompts from the official code and use LLM function,the results are quite good.
Recommended weight: 0.9-1
V2
Switched up the dataset this time. The old tags just weren't cutting it for the image features, so I fixed those and used a new model for training.other settings are basically unchanged, almost the same as v1.0
Recommended weight: 0.9-1
Recommended settings
Sampler: Euler A
Schedule type: Simple
Steps: 30
CFG: 6~7
Hires. Fix: R-ESRGAN 4x + Anime6B
Magnification: 2
Prompts
Prompt Prefix:
at0ka, 1girl, solo, school uniform, hat, long sleeves, brown eyes, boots, belt, knee boots, luna nova school uniformNegative Prompt:
nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, (((bad hands))), mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro,bad legs,multiple legs,multiplayer,V1
Recommended weight: 0.9-1
Recommended settings
Sampler: Euler
Schedule type: Simple
Steps: 30
CFG: 6~7
Hires. Fix: R-ESRGAN 4x + Anime6B
Magnification: 2
Prompts
Prompt Prefix:
at0ka, 1girl, solo, long hair, school uniform, hat, long sleeves, brown eyes, boots, belt, knee boots, shirt, luna nova school uniformNegative Prompt:
nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, (((bad hands))), mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro,bad legs,multiple legs,multiplayer,Description
Overall, it's good，looking forward to the base. This time, there was some underfitting because the dataset is quite large, and the step size was set too small. A larger step size should have resulted in a better fit.