Don't use it to post naughty pictures online please.
LCM does work. But sacrifices overall detail and promp coherence.
No special tricks where used to generated the images, no control net, no multi step process with img2img, no ADetailer, nothing just the basic models in SD WEBUI.
Recommendations
This can be used to generate images of 512/768, 768/512, 512/512 and anything in between, in all my testing no duplicate faces were generated.
Best CFG 7 - 9, i would not go any higher unless you wanna pump up the steps too.
Any checkpoint works but you may have to adjust the weight in order to get it to look right, the max usable weight is 1.3.
I recommend Restart/DPM++ 2M for the first pass and Restart/DPM++ 3M SDE for the Hires.fix pass, this will give you the best results.
Don't go above 2.0 times the first pass resolution, is better to pass it to img2img or use some other tricks to obtain more detail.
Extra notes.
The max resolution i tested is 960, it looks good, but expect duplicated subjects and faces.
If you want better face closeups i suggest you to use ControlNet, sd 1.5 is notorious for generating bad face closeups.
描述:
Brand new training process, way better than before.
Similar data set but bigger.
训练词语: sgwver
名称: SgWver_v3_locon_64_64.safetensors
大小 (KB): 101023
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
