For business inquires, commercial licensing, consultation and large scale image captioning for datasets contact me under [email protected], for custom LoRAs visit my ko-fi page.
Follow me on Twitter: @YamerOfficial Discord: yamer_ai
If you have enjoyed this checkpoint:
--> REDESTRIBUTION OF THIS MODEL TO PLATFORMS OUTSIDE CIVITAI AND SELLING IMAGES WITHOUT MY WRITTEN CONSENT IS FORBIDDEN! <---
You can contact me on Discord: (yamer_ai), Twitter: @YamerOfficial, email: [email protected] or directly using the Civitai chat system for my approval.
This is a collection of SDXL and SD 1.5 models dedicated to furry art.
Built around the furry aesthetic, this is a perfect checkpoint for all the furry nsfw enthusiasts and SDXL users, try it yourself to see both quality and style.
Have fun using this model and let me know if you like it, all reviews and images created are appreciated! :3
The main goal of this model is to generate images with a cartoon-like aesthetic, emphasizing furry attributes in the main subject. The use of terms like "furry," "animal," and "furry girl/man" can enhance the furry style.
SD 1.5 Update Note:
The last version (SD 1.5) is great with all kinds of nsfw prompts to generate some truly beautiful images.
Now the checkpoint better understand words that are commonly used in nsfw art.
SDXL V1 and V2:
It is important to note that the main goal of this model is not to make NSFW content but this model can do NSFW images if required, for creating NSFW art in a specific style please consider using an SDXL LoRA model designed for that purpose; No LoRA were used to create the images in the showcase images.
𝓜𝓞𝓓𝓔𝓛 𝓡𝓐𝓣𝓘𝓝𝓖:
Quality: 8/10
Stability (Variety): 7/10
Flexibility: 7.5/10
CFG resistance: 15/30
Style: 8.5/10
Style Strenght: 8/10
\╭☞ \╭☞ It works best with:
LoRA: XL YAMER'S STYLE ♠️ Princeps Omnia LoRA (for sdxl)
Restore Face: Not required to generate high quality images (Not used in the current showcase.)
Clip skip: 1-2 (The model works well with clip skip set to both.)
SDXL Refiner: Not needed with my models!
Checkpoint tested with: A1111
Recommended settings:
Image Quality: 1024x1024 (for SDXL), 576x576 (for SD 1.5)
Steps: 40-150
CFG: 7-20
Restore Faces: No
Hires Upscaler: 4x_foolhardy_Remacri or 4xUltraSharp
Description
The first SD 1.5 checkpoint to be uploaded in this family of checkpoints.
FAQ
Comments (17)
very good, even on non furry characters
Which version is the SDXL version?
V-1 and V-2, it looks like
Nice!
something happened, this model used to work perfect, but now it messes up the final step. It works like normal right up until the end, and then partially reverts back to noise. Tried deleting and reinstalling. No help. Tried lora/no lora, with or without hi res fix, with or without upscaling. all does the same thing.
Try double-checking the scheduler? Normal scheduler for Euler and Karras scheduler when experimenting with KPM++ SDE?
@PinkiePie956 Usually use Unipc with automatic scheduling, I'll have to mess around with those when i get a chance.
I have noticed this too. I think it directly relates to the VAE, because whenever I load the VAE, it does this thing where it partially reverts back to noise and makes the entire image black-and-white. Not loading in the VAE seems to resolve the issue on my end.
a were flux version?
Is an update being considered? Could use something more precise.
Great works well with good promts.
This may be one of the best furry models you can find here.
really good!
@Yamer, if you have intentions of making another SDXL version of this model: There're some models that could be good option to use as a base...
Works amazingly well and not just for NSFW content. Made a couple of SFW Pg rated figures with it I am quite happy with. Versatile.
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.