/vt/ - Virtual Youtubers

>>44602776
Anyways, off the top of my head:
1. Use the NovelAI VAE
2. Your negatives look like the AOM2-ish negatives. Use whatever negatives the fat model recommends. If it doesn't recommend any, either find what negatives WD1.5 works best with, use the NAI ones HLL is a NAI retrain or mix them up. Newfriends don't remember what adding weight to negatives could do on NovelAI - deep fry shit.
3. Turn your scale down.
4. Try a different sampler? DPM++ SDE Karras 25 steps. Save you some time over Euler a.
>>44602946
Looks deep fried to me. There's your problem - applying an SD LoRA to a model that's an SD/WD merge.
>>44602951
>>44602125
>(bad_prompt:0.8),
>1. I've never done embedding.
That's an embed. You need it in your embeddings folder if you're trying to get "the same image" - assuming the anon that made it isn't using xformers.
>>44589003
Have a pirate. Have 8 pirates.