LoRA trained on Riven from League of Legends
requested by @bty_is_within_us
models used
anime: YabaL_Mix V3
2,5D: PastelDiffusedMix - V2.1, CamelliaMIx_2.5D - V2
realistic: Paragon V1.0
tags: winterblessed diana, 1girl,
optional tags: dress, pauldrons, long hair, white hair, forehead mark
negative embeddings: bad-hands-5, ng_deepnegative_v1_75t, bad-artist, EasyNegative
Recommended settings:
Make sure you are aware on the usage instructions of LORA
VAE: vae-ft-mse-840000-ema-pruned (for realistic models & 2,5D), kl-f8-anime2, blessed2.vae (for anime models)
Sampler: DPM++ SDE Karras or DPM++ 2M Karras(euler a for img2img upscaling)
Steps: 20 to 35
Clipskip: 2
Upscaler : GitHub - pkuliyi2015/multidiffusion-upscaler-for-automatic1111 4x-UltraSharp(for 2,5D & realistic), 4xAnimesharp(for anime)
CFG Scale : 5 to 9 (mostly 7)
LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8)
Denoise strength upscaling: 0.4 to 0.7
for full body shots i recommend using: ComfyUI Impact Pack
or the a1111 alternative GitHub - Bing-su/adetailer
Description
FAQ
Comments (4)
Whzt a beauty tysm :) perfect work <3
ay thanks :D
Sorry you probably get like 12 trillion notifications from me haha. Your lora are perfect for testing different models and styles etc and I figured I'd share for those curious on the various styles since there's a lot being posted the last couple of days
All good, I enjoy your work. It's also interesting for me to see what the LoRA is capable of. I'm not testing it as intensely as you do sometimes, so I really appreciate your efforts! It also inspires me to try more models to implement into my workflow, like Paragon or Darksun :D
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.