Sign In

Rev Engine PonyXL

Download

1 variant available

fp16 SafeTensor

Half precision, best balance โ€ข 6.46 GB

Verified:

You need these files to run this model. We'll show the best match for your preferences.

V1 โ€ข Pony_VAE_Standard_byStabilityAI.safetensors

159.59 MB

Downloads your preferred variants

Type

Checkpoint Merge

Stats

188

Reviews

Published

Mar 29, 2026

Base Model

Pony

Hash

AutoV2
C08544E510
default creator card background decoration
ArtInsp's Avatar

ArtInsp

This merge is inspired by Rev Animated - one of the favorite stylized checkpoints for SD 1.5.

Built on top of DucHaiten, Everclear and several carefully selected Loras to achieve that distinctive artistic style.

Base Model: SDXL 1.0 / Pony Diffusion V6 XL

Type: Stylized Checkpoint Merge

โœจSpecific:

  • Works great for artistic and stylized generations

  • Produces very unique aesthetic results when using LoRAs

  • VAE installation is mandatory for proper output


โš ๏ธ I M P O R T A N T !

Requires SDXL VAE, otherwise images will be washed out with white dots.

  • Recommended VAE:

Pony Standard VAE - specifically designed for Pony/SDXL models

https://civitai.com/models/660673/pony-standard-vae


๐Ÿ“ Note:

This is a reprint of a previously available model. Original upload by razzz (Jul, 2024) was removed by the creator, but the model remains popular in the community.


๐Ÿ† Main Settings:

  • Sampling steps: 30

  • Sampling method: DPM++ 2M SDE

  • Schedule type: Karras

  • CFG Scale: 2-4

๐Ÿท๏ธ Hires.fix Settings:

  • Upscaler: R-ESRGAN 4x+ Anime6B

  • Hires steps: 20

  • Denoising strength: 0.35

  • Hires Distilled CFG Scale: 3.5

  • Hires CFG Scale: 1.5-2


[ Mandatory Quality Tags ]

  • score_9, score_8_up, score_7_up, score_6_up,

  • source_photo, realistic, 1girl, full body

[ DanBooru Tags ]

  • Use DanBooru-style tags here

  • For img2img: Use WD14 Tagger with model wd14-vit-v2-git

https://github.com/Akegarasu/sd-webui-wd14-tagger

[ CLIP Description (optional) ]

  • Natural language description

  • For img2img: Use CLIP Interrogator with model ViT-L-14/openai

https://github.com/pharmapsychotic/clip-interrogator-ext

[ LORA ]

  • Add your desired LoRAs here


๐Ÿ’ก Tip: Combine 3-4 LoRAs from different groups.

Keep total weight โ‰ค 1.5-2.0 for best results.

๐ŸŽญ Group 1 - Style:

๐Ÿ’ก Group 2 - Lighting:

๐Ÿ–ผ๏ธ Group 3 - Concept:

๐Ÿ˜Š Group 4 - Expression:

๐ŸŒˆ Group 5 - Color/Theme:



โค๏ธ Artificial Inspiration by DORO