THIS IS A REPRINT!
Go to original author to check their other models or to support them.
This is a LoRA trained with frames from the official Overwatch animated shorts. The training data included male and female characters, with an emphasis on faces. Recommended strength is 1, with the trigger word '0v3rw4tch' optionally with '3d, lips, nose'
V2 Note: I retrained it with corrected settings so it is no longer overtrained. You can increase LoRA weight above 1 to make a stronger style, but I still recommend using strength 1.
ADetailer is very recommended for improving faces with this style. The main intent of this LoRA is to make beautiful faces.
How I generate images:
Local generation using reForge
Sampler: Euler Ancestral CFG++
Schedule type: Turbo
Sampling steps: 8
CFG Scale: 1.571428
Img2Img Upscale or Hires. fix: 1.5x at 0.428571 Denoising strength
If you use on-site generation or otherwise don't have CFG++ samplers, you can use CFG Scale 7 and achieve similar results.
If you like what this can do, please take a moment to post an image to this model, it helps me out a lot. Thank you!