Merge from Pony Diffusion V6 XL and custom LoRA.
This model goal is to get a generic anime 2D style and still be compatible with all LoRAs trained on Pony. Surprisingly, it improves Pony background drastically.
For a strong anime style, I recommend to start your prompt with :score_9, score_8_up, score_7_up, anime screencap
License (from PonyXL)
This model is licensed under a modified Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/) license.
The following modifications have been added to Fair AI Public License:
You are not permitted to run inference of this model on websites or applications allowing any form of monetization (paid inference, faster tiers, etc.). This applies to any derivative models or model merges. (Only exception Civitai)
Description
FAQ
Comments (7)
Samples looks amazing as always, I will be working on some images too, thanks for sharing it! 👊
Thank you, always a pleasure to see people use my work.
Oh I'm curious about this, but a question, did you add new characters or styles based on the Loras you have done? I feel that Pony lacks is the variety of innate characters and styles.
LoRA added contain some characters but it's max 1 or 2 pictures for each character so not enough to have an effect if your prompt their name if they are not innate Pony.
For style, except "anime screencap" no trigger were used for the LoRAs so you can't prompt them either.
can you do Kena: Bridge of Spirits?
Why I can't use it?
New system to host checkpoint on generator. Nobody auction buz on this one for this week.
Details
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.