
This is a Lora trained in Fluxgym it works for gguf and dev fp8 and 16
Usage Tips for FLUX:
-
The LoRA weight I have been using is 0.7, to 1.8 but feel free to try and experiment!
-
I have used ComfyUI an invoke generated pictures and the settings im using are:
Sampler: dpmpp_2m
Scheduler: Karras
Steps: 20PS. I notice that with guidance scale below 3 the image become gibberish. ;)
-
Example prompts used:
"bubu_dudu panda and bear hand-drawn illustration, in a cozy mountain cabin, holding a sign saying "che bello il relax" next to a crackling fireplace"
描述:
First version
训练词语: bubu_dudu
名称: bubu-dudu.safetensors
大小 (KB): 38845
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
原文链接:https://1111down.com/1176537.html,转载请注明出处