The model that can generate images with simple prompts.
The following settings are recommended:
Sampling method: DPM++ 2M SDE
Schedule type: Karras
Sampling steps: 15
CFG Scale: 2.25
Negative prompts:
embedding:BeyondSDXLv3 embedding:unaestheticXL_Alb2
If you want more details
Sampling steps: 30
CFG Scale: 2.25~8.0
If you are using LoRA, the following settings are recommended:
Sampling method: Euler
Schedule type: Automatic(Exponential)
Sampling steps: 30
CFG Scale: 4
I merged the following two models
Thanks to the model providers
国风4 GuoFeng4 XL v1.2 56%
Atomix Anime XL v1.0 44%
Description
FAQ
Comments (3)
really Good
Hellow i have two problems, i need a character see from left or right, i need image seen from the side, and it always comes out straight even if I specify, and I need it to appear with a surprised face and it comes out serious even if I specify, do you know if there is a way to write so that I can be understood?
Unfortunately, this model does not have a lot of facial expressions.
I recommend merging it with other models.
So I made "Gufeng 3D Cartoon XL".
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.