Pony Realism – v21 Lightning 4S VAE

Related Keywords & Tags

Recommended Prompts

score_9,score_8_up,score_7_up,BREAK
cinematic film still cinematic photo breathtaking score_9,score_8_up,score_7_up,BREAK,8k,masterpiece,high quality,long hair,necklace,hoop earrings,thigh strap,shirt and jeans,skin pores,laying in a confy chair,garden,detailed skin,depth of field,highly detailed,highly detailed . 35mm photograph,professional,film,film grain,4k,highly detailed . shallow depth of field,bokeh,vignette,high budget Hollywood movie,cinemascope,moody,epic,gorgeous,grainy

Recommended Negative Prompts

score_4,score_5,score_6
score_1,score_2,score_3,distorted,grainy,drawing,noisy,blurry,sketch,text,impressionist,deformed,painting,soft,ugly,crayon,graphite,anime,cartoon,graphic,abstract,glitch,mutated,disfigured

Recommended Parameters

samplers DPM++ SDE, DPM++ 2S a Karras, DPM++ SDE Karras, DPM++ 2M SDE Karras, DPM++ 2M SDE Exponential, DPM2 a, DPM++ 2S a, DPM++ 3M
steps 20 – 30
cfg 6-7
clip skip 2
vae sdxl_vae.safetensors
resolution 1280×768 | 768×1280

Tips

  • I recommend using female/male instead of woman/man.
  • At longer distances Adetailer is recommended.

Version Highlights

🚨 This is the 4 step Lightning version.

ℹ️ This model will only work with the latest A1111/Forge webui

️Required settings:
· Samplers:

  • Euler A

  • DPM++ 2S a

  • DPM++ SDE

  • DPM++ 2S a Karras

· Steps: 5

· CFG: 1-3 Increasing CFG will fry the image.

Creator Sponsors

All sponsors are not affiliates of Diffus. Diffus provides an alternative online Stable Diffusion WebUI experience.

🏋️‍♀️ For training LoRas using the model go here

💕This is probably going to be the last version of the model for the moment as Im quite happy with the result. Thanks for downloading and I hope you enjoy it 🙂

If you want to support me feel free to do so on Ko-Fi 🙂

⚠️ Please read the description

♻️ v2.1 Is a major rework of the model.

  • Main version has the most detail at the cost of Sampler compatibility

  • Alternative version works on most Samplers at the cost of some detail

ℹ️ This version leans more towards Pony for more overall variety, but maintains the realistic quality.
ℹ️ Example images are without Adetailer

📍Recommended Parameters For the MAIN version:

· Samplers:

  1. DPM++ SDE

  2. DPM++ 2S a Karras

  3. DPM++ SDE Karras

  4. DPM++ 2M SDE Karras

  5. DPM++ 2M SDE Exponential

  6. DPM2 a

  7. DPM++ 2S a

  8. DPM++ 3M *

I DO NOT recommend the use of the following samplers (weak detail):

  • Euler a

  • Euler

· Steps: 20 – 30 .

· CFG: 6-7

· Clip Skip: 2
· Resolution: I have been using 1280×768 | 768×1280

· I recommend using female/male instead of woman/man

ℹ️ Samplers not listed on the recommended won’t work or need some tweaking in CFG or steps.

This version does not need any trigger words, and as like most Pony models it uses the following prompt style:

Positive:

score_9, score_8_up, score_7_up, BREAK

Negative:

score_4, score_5, score_6

💪The model has more general variety, creativity and better prompt adherence.

At longer distances ADETAILER is recommended.

️BUZZ FOR BEST IMAGES⚡️

Leave a Comment

Models in the Same Collection

Up close view of a green-skinned woman yelling, AI generated image using Stable Diffusion.

Pony Realism - v21 Lightning 4S VAE

AI generated image of a redhead woman in a flowery dress standing in a country landscape, created using Stable Diffusion.

Pony Realism - v21 Alternative VAE

Elven warrior with pointed ears kneeling in the forest while wearing silver armor and leather pants created using Stable Diffusion AI.

Pony Realism - v21 Main VAE

Model details

Model TypeCheckpoint
Base ModelPony
Model Hash9d82192162
Model Versionv21 Lightning 4S VAE
Trained Words
Creator
ZyloO's Avatar
ZyloO
ReferenceCivitai

Share to

Model Review

Contributor

Picture of Kate Thompson

Kate Thompson

Images by the Same Model