RizDraws - PonyDiffusionXLV6 - 1.1 - 000014
Empfohlene Prompts
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_anime, outside, looking at viewer, solo, female
Empfohlene Negative Prompts
embedding:XL-aidxlv05_neg, anthro, 3d \(artwork\), bulbous nose
Empfohlene Parameter
samplers
steps
cfg
resolution
Empfohlene Hires (Hochauflösungs-) Parameter
upscaler
upscale
Tipps
Sampler from images is done with Restarts with segments of [3,2,0.06,0.30], based on the Restarts paper.
Initial resolution typically 768 x 1152 or vice-versa, upscaled by 5/3 (approximately 1.66) to keep pixel count near 1024 x 1024.
Second sample pass uses same parameters but at approximately 0.35 denoise.
Use a facedetailer for added detail.
Recommended LoRA strength is 1.
Versions-Highlights
Initial Version
Backgrounds have middling detail
I might just suck at prompting on pony, but '3d' in negatives improves stability
Ersteller-Sponsoren
LoRA trained on RizDraws' artstyle for ponydiff: https://civitai.com/models/257749
LoRA trained on RizDraws' artstyle for ponydiff: https://civitai.com/models/257749
Artist: https://x.com/Rizdraws | https://www.rizdraws.com
Because of my lack of experience and time, the version number may be based on changes that have made certain aspects worse. As such a previous version may perform better than a later version.
I'm still learning the ins and outs of the model and LoRA training in general, please leave reproducible feedback or tips so that I may improve over time.
Check the "About this version" section for any quirks or pitfalls I'm aware of or have experienced.
Some Q's:
What's your workflow?
Sampler from images is done with Restarts with segments of [3,2,0.06,0.30], which are values from the paper on Restarts
Initial resolution is typically 768 x 1152 or vice-versa and upscaled by x(5/3), I try to keep the pixel count around 1024 x 1024 for initial gens and adjust the upscale ratio as needed
Upscaler is usually 4x_fatal_Anime_500000_G or 4x_NMKD-Siax_200k
Second sample pass is the same as the first (params are on civit's meta interface) but at ~.35 denoise
A facedetailer is used
I use ComfyUI, sorry
What strength should I be using?
1
Modell-Details
Diskussion
Bitte log in um einen Kommentar zu hinterlassen.










