If you like my work, drop a 5 review and hit the heart icon. it's free and keeps me motivated
All my models are officially hosted and maintained by me on Tensor.art . use my Exclusive and public model for free on tensor.art
v5.0 civitai onsite generation enabled : 04/01/25
v5.0 final release : 01/01/25
v5.0 pre relelase update : 25/12/24
Check tensor.art for V1,V2,V3 online generation support
You can run Prefect Pony XL and use its API on SinkIn
currently, only v5 and v4 are available for civitai generation.
v3,v2,v1 are retired from civitai generation. check other version details for alternative on site generation service.
WIP: Realistic
V5 Update :
onsite generation : https://tensor.art/models/815661199413897287
pre-release : https://tensor.art/models/810892802167877454
Added trained Lora
Cleaned style
Baked in VAE
Extra trained data of 15000 steps
Better Lora support.
V4 Update :
onsite generation : https://tensor.art/models/794513755405953653/Prefect-Pony-XL-v4
Added trained Lora
Cleaned style
Baked in VAE
Extra trained data of 15000 steps
Better Lora support.
V3 Update :
onsite generation https://tensor.art/models/772139385270444718
added some style to it
should give better face and eyes
better NSFW supports
wide range of Lora support
V1 lightning :
8-steps
DPM++ 2M
V2 update:
onsite generation https://tensor.art/models/754887012743423435
has less style influence
can work with wide range of loras
better anatomy
better color
V1 update:
On site generation closed for v1 on civitai for limitation of civitai.
try tensor.art if you want to use the online generation for v1
https://tensor.art/models/724940954567461228/Prefect-Pony-XL-v1.0
If you like my work then drop a 5 review and hit the heart icon. it's free and keeps me motivated
Suggested settings:
I had CLIP skip 2 on every image
I had ENSD: 31337 all of them
All of them had highres.fix or img2img at higher resolution.
I don't use restore faces
I use afterdetailer for face details
Tiled diffusion for img2img upscaling and sometimes Noise Inversion for some more extra details.
4x-Ultrasharp upscaler
NOTE: if you find any prompt of the preview images look familiar it's because I've taken them from other model review images, Credits to the original authors. Thanks for the benchmark.
Commission open in Patreon.
Get early access and Exclusive NSFW Lora in my Patreon .
Support my work by joining any one of them and get early access to all my upcoming loras and other perks such as fan requests and Discord role.
Join my Discord Server
Description
Setting suggestions -
Sampler : DPM++ 2M
CFG Scale : 2-3
Steps : 10-20
Adetailer
FAQ
Comments (38)
In this part, add a link to the exact model uploaded to TensorArt please, I cannot find it there.
[…]
try tensor.art if you want to use the online generation for v1
[…]good idea
One of the best Pony models IMO. So underrated. Many thumbs up.
nice
Great model, might be my fav next to autismmix!
have you thought about making a turbo version? one that works with even lower settings
From my testing default models are the best. Those faster lightning or turbo models are a step down.
If you can actually manually use them (not as "draft mode" on civitai), lightning loras work very well with Goofy's models. 8 steps you barely can see the difference, 4 steps change the style but are still decent.
Definitely my new favorite model!
Built in VAE ?
yes
really detailed and goated
the name is prefect instead of perfect, can you fix that please
Super clean and smooth looking general purpose illustrated look. Great for getting the most out of western illustration style LoRas.
My favourite model 5 stars!!!
Is v1.0 not available for on-site generation anymore?
I had old pictures generated using it, and the results were better, softer colors and lighter lines
as of now civitai only lets me run single version. you can still use the v1 on tensor.art
check the description
I haven't been using this model for very long, but so far I can say that it's no worse than AutismMix! And that's very good👍
What model do you usually use?
I like it more than autism thus far, good job 👍
Ty
Using it with HiDiffusion + Euler a, draws really great backgrounds, and clean lines. Loyal to the prompt at CFG 7. Recommend 25~30 steps. ESRGAN 4x Ultrasharp or Anime6B both works well.
Comparing to tPonyNai3, generally the style is more western. Style is more oil paint-y using same prompts. Does an superior job at detailed, atmospheric backgrounds.
hey bro cómo se utiliza esto
What UI are you using to be able to use HiDiffusion? I'm currently using Forge, and it seems it's not supported yet. :/
@nor1c I use sd-next and it comes out of box
Hardcore Hentai SD1.5 with add_detail is still better. For some reason, Pony_DetailV2.0 doesn't work at all. But since there's nothing better for Pony, it'll do
Great for most prompts I want
9.5/10
9.6/10 like
What does ENSD: 31337 do?
It shifts the seed. You don't have to bother, unless you want to recreate the image with it.
It makes it so stable diffusion doesn't crash you'd better leave it forever
great globally, maybe better then pony itself
Wonderful and clean results with this one!
Great stuff