Type | |
Stats | 48 |
Reviews | (7) |
Published | Sep 1, 2024 |
Base Model | |
Training | Steps: 9,900 Epochs: 1 |
Usage Tips | Clip Skip: 1 Strength: 0.8 |
Hash | AutoV2 D62642A7E4 |
The Dancer/Сhoreographer/Actress
Due to the new site policy, in newly published models, there will be only 2-5 pictures, as an example. so as not to "offend" anyone.
I still have many unpublished LoRa models for SD v1.5. I will probably publish them gradually, too, but it is already clear that we need to gradually switch to the FLUX model, since it is obvious that the result itself is much better there, but the degree of similarity, if you make any person, is also much higher. But I can't train models for FLEX on my home computer yet, only here on the website. and it takes a lot of BUZZ. So, any help is welcome!
the training was on a model - CyberRealistic 3.1 in resolution 640x960, and used a dataset of 165 images.
I'm Render this on - EndlessReality v6
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 36, Denoising strength 0.35, CFG Scale 3.5-8.5
the weight of the model is approximately 0.75-0.85