Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
prefectPonyXL_v3.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<prefect3-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
Goofy_Ai
on Civitai
Prefect (sic) Pony V3 by GoofyAI is a pony diffusion fine tune with better support for loras, and better eyes and faces than the previous versions. Clipskip 2 is recommended.
Creator notes
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 . use my Exclusive and public model for free on 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 for V1,V2,V3 online generation support You can run Prefect Pony XL and use its API on 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 : pre-release : - Added trained Lora - Cleaned style - Baked in VAE - Extra trained data of 15000 steps - Better Lora support. V4 Update : - onsite generation : - Added trained Lora - Cleaned style - Baked in VAE - Extra trained data of 15000 steps - Better Lora support. V3 Update : - onsite generation - 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 - 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 if you want to use the online generation for v1 - 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 Get early access and Exclusive NSFW Lora in my 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
51,693 downloads · 6,913 likes on Civitai
SHA256
E31A2563F0749CB4351A4A024780C025B9242E08A3A458F3B83A4B8516BD194B
ModelTrends.ai Model ID
#4484
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
196401406
Size
896x1152
Prompt
score_9, score_8_up, score_7_up, solo, YaeMikoFox, animal, animal focus, earrings, jewelry, headgear, horns, sunglasses, pince-nez, multiple tails, cityscape, night, rain, neon lights <lora:YaeMikoProgenitor_pdxl_Incrs_v1:1> <lora:YaeMikoFox_XLPD:1.4>
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
6.5
Seed
3279018798
Size
832x1216
Clip skip
2
Prompt
score_9, score_8_up, score_7_up, Android girl, pixel face, screen face, robot body, metal skin,
Negative prompt
score_6, score_5, score_4, source_cartoon, 3d , (censor),monochrome,blurry, lowres,watermark,(lamia,scales,mermaid,snake tail),(worst quality:1.4),(low quality:1.4),ugly,bad face,morbid,extra fingers,mutilated,mutilated hands,poorly drawn hands,poorly drawn face,blurry,extra limbs,cloned face,gross proportion,malformed limbs,missing arms,missing legs,missing fingers,(extra hands:1.1),too many fingers,extra legs,extra feet,fused fingers,censored,EasyNegative,pubic hair,scales, muscle, ,, four toes, four fingers, extra fingers, six fingers, Imperfect eyes, bad eyes, badly drawn eyes, distorted pupils, bad pupils, NEGATIVE_HANDS, human, humans, human girl
Settings
Sampler
DPM++ 2M
Steps
20
Guidance
7
Seed
1709835912
Size
1248x1824
Prompt
score_9,score_8_up,score_7_up, 1girl, alternate costume, beanie, black choker, black hair, black hat, black sweater, bow, brown eyes, buttons, choker, collared shirt, covered mouth, cross, cross earrings, earrings, floral background, hair between eyes, hat, hat bow, jewelry, long hair, looking at viewer, mask, mouth mask, pink background, portrait, prototype design, red bow, shirt, sidelocks, solo, spiked ear piercing, spikes, studded choker, sweater, twintails, white shirt
Negative prompt
realistic,monochrome,greyscale, artist name, signature, watermark,
Settings
Sampler
DPM++ 2M
Steps
25
Guidance
7
Seed
3605004383
Size
2496x3648
Weight used
1
Prompt
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, high quality, 1girl, solo, on water, legs bent, arms around legs, novuschroma65 style watercolor, dripping watercolor, color drops on background, abstract, paint bubbles,
Negative prompt
civit_nsfw, bad quality, blurry, signiture, text, watermark, extra limbs, bad focus, childish, poorly drawn, nsfw, naked,
Settings
Sampler
DPM++ 2M
Steps
20
Guidance
7
Seed
425529227
Size
1248x1824
Prompt
score_9,score_8_up,score_7_up, <lora:mamimi_mamamimi_style_pdxl_goofy:1> 1girl, breasts, ringed eyes, solo, cleavage, makima (chainsaw man), hair twirling, yellow eyes, red hair, veiny breasts, large breasts, pink sweater, from above, downblouse, white background, looking up, blush, sweater, open mouth, playing with own hair, veins, simple background, sensitive, off-shoulder sweater, off shoulder, braided ponytail, bare shoulders, lipstick, sidelocks, makeup, looking to the side, red lips
Negative prompt
realistic,monochrome,greyscale, artist name, signature, watermark,
Settings
Sampler
DPM++ 2M Karras
Steps
14
Guidance
4
Seed
929039484
Size
832x1216
Clip skip
2
Prompt
score_4,score_5,score_6,score_7_up,score_8_up,score_9 ((masterpiece,best quality,ultra detailed,highres,HD,4k:1.2)), 1girl, solo,solo focus,girl focus,face focus, Kohaku(iX),((brown hair)), orange eyes, ponytail, sidelocks,hairband,very small breast,petite, Maid outfit,Sleeveless, maid headband, frilly apron,Short sleeves, short skirt, thighs, inside the cafe, ((Make a heart symbol with both hands, heart with both hands,heart hands,heart symbol,heart,heart effect,)), blush,shy,smile,((wink,closed one eye)),
Negative prompt
(Macho, muscular, old man, fat man,Nostrils, ,text,yuri,roll one s eyes:1.5),(worst quality, low quality:1.4), (patreon username, patreon logo, signature, watermark,easynegative,negative_hand-neg, bad-hands-5,low quality,bad-hands-5,extra limbs,missing limb,extra digit,fewer digit,missing digit,missing fingers,mutated hands and fingers,fused limb,bad hands,long neck,long body,bad anatomy,disfigured,deformed,poorly drawn,mutation,extra nippless,extra breasts,disembodied penis,:1.4)
AI Models for Image, Video & Text Generation
prefect3 xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models