Our iconic meme tribute !
Negatives in use RZ General & RZ forAnalog
Grids comparing the 80 and 24 dim :
A photo portrait of rzju4n
Negative prompt: rz-neg-foranalogportrait, bw, low resolution, b&w, black and white
Steps: 20, Sampler: Euler a, CFG scale: 8, Seed: 2121, Size: 512x768, Model hash: 4711ff4dd2, Model: v2-1_768-nonema-pruned, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: rzju4n_80-40(ac4bbd6becbe), AddNet Weight A 1: 0.85, AddNet Weight B 1: 0.85
rzju4n, photo portrait , wearing a futuristic mecha outfit, sci-i , cyberpunk, biomechanical
Negative prompt: rz-neg-foranalogportrait
Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7.5, Seed: 5242, Size: 512x768, Model hash: 4711ff4dd2, Model: v2-1_768-nonema-pruned, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: rzju4n_24-12(8a94686107d8), AddNet Weight A 1: 0.85, AddNet Weight B 1: 0.85
rzju4n, photo portrait , wearing a futuristic mecha outfit, sci-i , cyberpunk, biomechanical
Negative prompt: rz-neg-foranalogportrait, bw, low resolution, b&w, black and white
Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7.5, Seed: 5452, Size: 512x768, Model hash: 4711ff4dd2, Model: v2-1_768-nonema-pruned, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: rzju4n_80-40(ac4bbd6becbe), AddNet Weight A 1: 0.85, AddNet Weight B 1: 0.85
Have a good tuning !
romerorz.art - Twitter - DeviantArt - Gumroad
Description
FAQ
Comments (5)
1.5 when?
I tried making a Lora on a face for SD2.1 and it wasn't working - at all. SD1.5 was fine ... can you point to how you train your Lora?
same here. Cant get much likeness from selftrained 2.1 embeddings and loras (1.5 is fine)
Not working for me, tried in the same model you used and others, it's just not working at all :\
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.