There was something without brains that creates, constantly, new accounts, and put one star in the reviews. of course, without any arguments. not because the model is bad, but because he is an idiot, and he tries to prove it with all his actions.
Singer
the training was on a model - CyberRealistic 2.0.
I'm Render on - EndlessReality
if you want to get speed, drive a sports car
if you want to drive off-road, take an SUV
if you want to hammer a nail, take a hammer
it's the same here - if you want to get results, read the recommendations and follow them
I do not recommend using my LoRA with model RealisticVision
personally, I most often perform generation with parameters: DPM ++ 2M Karras, Sampling Steps 35, Denoising strength 0.35, CFG Scale 3.5-4.5
evaluation of the model is welcome
Description
FAQ
Comments (5)
You made it! Looks great! Thanks!
Someone has to some Art with that where she stands over Vecna :D
Do you wanna feel how it feels? (Yeah, yeah, yo)
I’ve been a fan of Kate Bush since 1984.. I can’t recommend this on the strength of one single example image where the face slightly resembles her, but I will try this out. I have done some extensive AI image generation of her in the past year. I’ll let you know what I think of your LoRA.
After trying this out on a few different realistic models, I have to conclude that although I’m getting a good likeness to Kate, it’s obvious that the model was trained on low-resolution images- I can’t seem to get any of them to generate images that aren’t fuzzy, or blurry on the edges. Any recommendations for fixing this? My recommendation is that you continue training this LoRA with high-resolution images. I could point you to a fan site where there are many high-resolution images uploaded there.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.