models/RizDraws - PonyDiffusionXLV6 - 1.1 - 000014

RizDraws - PonyDiffusionXLV6 - 1.1 - 000014

|
12/13/2025
|
5:13:33 AM
| Discussion|
0
Anime-style Egyptian female kneeling in desert, with tan skin, white hair, red eyes, wearing a white robe and Egyptian collar, sunbeam in background.
A cat girl character with black hair, green eyes, round rimless glasses, cat ears, and tail, wearing an off-shoulder green sweater, kneeling barefoot.
An AI-generated image using stable diffusion of a confident anime character smiling while looking back, wearing a green and cream outfit with a black and green hat.
An anime girl with blonde hair, in a dynamic pose, against a beautiful outdoor scenery, generated by AI using Stable Diffusion.
Anime girl in denim outfit with blonde hair and confident smile. AI generated image using Stable Diffusion.
An anime-style character with short black hair and a headband, smiling confidently. AI generated image using stable diffusion.
An anime girl with a stylish outfit, generated using stable diffusion AI.
Illustration of an anime girl generated by AI using Stable Diffusion. The girl has blonde hair, blue eyes, and is floating in the air with a confident smile, wearing a blue jacket, a striped undershirt, black shorts, and black stockings.
Anime girl with long orange hair wearing a blue baseball uniform. This is an AI generated image using Stable Diffusion.

Recommended 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

Recommended Negative Prompts

embedding:XL-aidxlv05_neg, anthro, 3d \(artwork\), bulbous nose

Recommended Parameters

samplers

Restarts, DDIM

steps

30

cfg

7

resolution

768x1152, 1152x768

Recommended Hires (High-Resolution) Parameters

upscaler

4x_fatal_Anime_500000_G, 4x_NMKD-Siax_200k

upscale

1.6 - 1.67

Tips

Keep initial pixel count around 1024 x 1024 for initial generations.

Use a facedetailer for improved face details.

Strength should be set to 1 for the LoRA model.

Secondary sample pass uses the same parameters as the first with ~0.35 denoise.

Version Highlights

Initial Version

Backgrounds have middling detail

I might just suck at prompting on pony, but '3d' in negatives improves stability

Creator Sponsors

LoRA trained on RizDraws' artstyle for ponydiff: https://civitai.com/models/257749

Artist: https://x.com/Rizdraws | https://www.rizdraws.com

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:

  1. 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

  2. What strength should I be using?

    • 1

Previous
Chroma-Flash-Heun - Rank 256
Next
Dark Dreams in Flux - v2.0

Model Details

Model type

LORA

Base model

Pony

Model version

1.1 - 000014

Model hash

258a0698ba

Creator

Discussion

Please log in to leave a comment.

Images by RizDraws - PonyDiffusionXLV6 - 1.1 - 000014

artist Images

style Images