JAFA Mix - v3.0
Verwandte Schlüsselwörter & Tags
Empfohlene Negative Prompts
watermark, blurry
Empfohlene Parameter
samplers
DPM++ SDE Karras, Euler a
steps
20
cfg
7 - 10
resolution
1024x768, 896x512, 768x512
vae
kl-f8-animev2 - baked in
other models
JAFAMix_v3b (bbdec0f0f7)
Empfohlene Hires (Hochauflösungs-) Parameter
upscaler
4x-UltraSharp, R-ESRGAN 4x+ Anime6B
upscale
2
steps
10
denoising strength
0.3 - 0.7
Versions-Highlights
More models added to the mix, still has the rcnz_niji lora in there as well, but now more diluted
Ersteller-Sponsoren
Update v4 - Added 3 more models to the mix (as per version info), fixes the issue introduced with the lora from v3 where the eyes would end up far too sparkly, and gives more detail in the backgrounds. Still works with the rcnz_niji style trigger word.
This mix was going to be Dumb Monkey v2, but ended up as a more pure anime mix, hence the acronym, "Just Another F***ing Anime" Mix
kl-f8-animev2 VAE is baked in, and both ckpt and safetensor versions are pruned to fp16
Mitwirkende
Modell-Details
Modelltyp
Checkpoint
Basismodell
SD 1.5
Modellversion
v3.0
Modell-Hash
73b7974094
Trainierte Wörter
rcnz_niji style
Ersteller
Diskussion
Bitte log in um einen Kommentar zu hinterlassen.