Serene版本v2.0 (ID: 830307)

Welcome!

Thanks for checking out my latest project!  If you're new to my models, my focus is to blend styles together in interesting ways to get consistent great-looking results without the need to pile on a big LoRA stack.  My future plans for this model are to incorporate a couple of new style LoRA that I'm working on.  The vibe for this model feels like it fits in between my Siren and Serendipity models, so I decided to release it separately. 

 

All sample images were generated with no LoRA or TI, and prompts are included for testing.  They do have Adetailer and Hires fix turned on.  Faces still generally look OK without Adetailer, but I recommend using it if possible.  I use face_yolov8s.pt for most of my uploads.

 

If you are new to Pony, here are some tips:

Scoring - Use score_9, score_8_up, score_7_up, score_6_up, score_5_up in your positive prompt instead of SD1.5/SDXL quality tags.  Or use Zovya's Tis that do this for you with fewer keystrokes.

 

You can also use some of the baked in sources and content ratings  to control  the kind of output you get: 

Sources - 'source_pony', 'source_furry', 'source_cartoon' and 'source_anime'

Ratings - 'rating_safe', 'rating_questionable' and 'rating_explicit'

 

 

My Usual Settings /Other Tested Options

Sampler -DPM++ 2M SDE Karras /Restart /Euler A

Steps - 30--50 (30 for fast gens to test ideas, 50 for things I may save/post)

Resolution -896x1152, 832x1216 (or flip for landscape)

 

Hires.fix:

Upscaler - Ultramix_balanced, 4x_Ultrasharp

Steps - 10-20

Denoise -.3-.4

Upscale by - 1.5 - 2.0

描述:

Spent some time working on getting the art style closer to where I want it to be. Let me know what you think in the comments.

训练词语: