Online generation
Recommended Settings:
Sampling Method: DPM++ 2M SDE
Schedule Type: SGM Uniform
CFG Scale: 6-4
建议设置:
采样方法：DPM++ 2M SDE
Schedule type：SGM Uniform
CFG Scale：6-4
If you like this model, you can support me here.
If you'd like me to develop a personalized LoRA model tailored to your needs, check out my custom service offerings on Patreon!
Description
FAQ
Comments (9)
merge recipe?
Basically, it's noobai V1.1+GENESIS V0.4 0.5 weight+GENESIS V0.2 0.2 weight
@EWIGKEIT0 Thank you :) And thank you for linking in the other post the hugginface with Genesis's art style tags. I barely use any other models, yours is just too good.
@allamalla You're welcome! I'm glad you like it. :)
@EWIGKEIT0 is ntdmix V1.5 then basically noobai 1.1 + GENESIS V1 0.5 weight + GENESIS V0.4 0.2 weight?
@deitychaser Haha, you're getting really close! To be honest, I made this version a long time ago and don't remember the exact recipe myself. I threw a couple of other checkpoints into the mix as well, besides my GENESIS models. ;)
@EWIGKEIT0 I see! Especially the vpred is simply great in how artsy it is. Some results gave me angle wise the impression that there is bit of aesthetic modifier lora mixed into it.
@EWIGKEIT0 Also do you maybe have an advise on how to merge a lokr like Genesis properly to a model? Are there any data blocks of the lokr I should disable completely?
@deitychaser I didn't disable any data blocks. I just used the merge.py script from the LyCORIS to bake the LoKR into the checkpoint at a specific weight.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.