This is a LoRA trained with images by the artist Marushin (Denwa0214). Recommended strength is 1.
V2 - Now capable of stronger style for very fine-tuned checkpoints. Use 'm4rush1n d3nwa0214' near beginning of prompt for intended effect.
How I generate images:
Local generation using reForge
Sampler: Euler Ancestral CFG++
Schedule type: Normal
Sampling steps: 30
CFG Scale: 1.571428
Img2Img Upscale or Hires. fix: 1.5x at 0.428571 Denoising strength
ADetailer to improve faces
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!
Description
FAQ
Comments (3)
Very nice LORA!Thank you!
It works well with NAI, however, I don't find it as effective as NAI with my beloved waiNSFWIllustrious_v80.Could you please make any adjustments for this?
Sorry about that! I am still experimenting and learning about training LoRA. If I manage to make a stronger style version, I will of course upload it, but in the meantime you can try using the artist tag 'marushin \(denwa0214\)' in your prompt for stronger effect.
Thank you! I have tried that prompt but it is not as beautiful as this Lora.
I am looking forward to a version with a stronger style as I love this artist! I hope the effect will be strong not only in NAI but also in IL and WAI!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.