This is an e621 model, use e621 tags. works well with furry artist tags (inside of fluffyrock) struggles with SD artists.
Redwater :
My original model and still my most loved, stick with this one if you want an overall model and use prompts to push it (say towards realism)
still does adult stuff the best and is better at emulating artist styles/most affected by artists tags.
Redwater703 :
A push towards realism, the idea behind this one was to have a model that defaults towards realism and then you can use artist tags to make interesting combos.
-
Suggestions for generation (all links are Civitai links):
A negative e621 inversion is very useful, I highly recommend boring_e621_fluffyrock_v4 as this model is a fluffyrock model at its core
If that one is causing problems then BWU from furtastic is also very good.
1024x768 (or vice versa) is the max I would go for txt2img generation, you're better off with limiting either dimension to 768 to prevent weirdness and then upscaling.
Credits:
WithoutOrdinary - For their fluffyrock model, this model uses fluffyrock-576-704-832-960-1088-lion-low-lr-e86-offset-noise-e71.
Freek22 - For their Newdawn model, this model uses newdawn_52aurora.
DominoPrincip - For their Opiate model, this model uses opiate_V30PrunedFp16.
A_B - For making stable diffusion fun and the advice on merging ^^ - A_B's models are here.
I recommend taking a look at the above models/creators and giving their stuff a try and a thumbs up.
Edits/updates:
Removed walls of text from description.
Removed advice on human in negative, I'm finding that it reduces the quality of the picture at least sometimes.
Description
FAQ
Comments (15)
this model is easy to generate images.
I really liked the strong fluffy fur rendering tendency and the precise eyes and have have balanced background.
Oops I thought I had said something on this comment. thanks A_B! ^^
Just want you to know that this is a fantastic merge. Seriously better than anything else I've tried so far. Great work. :D
Aww thanks! I hope it brings you much fluff. ^^
Is it possible to provide a file to see how strong certain tags are? like how many tags (or images trained) are for certain artists?
The model is a merger so unfortunately I have no images or lists. however the furry model used was fluffyrock which does have an autocomplete csv file which basically lists the tags (I did use a 3m model so sadly the tag representation size is likely inaccurate)
Another good shout out is chilon249's Yiffymix they have a link near the top of the description that tries to give an idea of each artists impact (using images, its really good) we both use fluffyrock so there should be some similar tracking.
I hope this helps. ^^
This model is truelly amazing. The generated image looks really crispy even with prompt and the detail is astonishing. Really love it
Thanks Kein! ^^
I've found that when I'm creating stuff with my usual stuff, and I see the overall feel of the work just begging for a grittier, darker, less refined look, like a sewer, cyberpunk, or post-apocalyptic world, switch over to this model, and it delivers in spades!
With very little coaxing, it totally feels like an unsanitized, left-to-its-own-devices, living world, with all the nasty filthy unpolished bits that come with it. I'm in love.
Looking forward to pushing it the other direction... Shiny, sterile, future hyper-utopia, not a speck of dust... can it deliver? Will find out!
I sacrificed around 30% of the furriness for opiate and don't regret any of it ^^ its a dark realism model (nothing crazy just monsters/zombies mixed with realism) even new dawn has some post-apocalypse undertones.
It's great to see someone has got out their spade and went digging, careful of what you might find. ^^
It's a really powerful semi-realistic model for creating furry art. It's become one of my favorite! Prompts need to be chosen carefully but if you do it right, the variety and quality is just perfect for a lot of furry characters and species. <3
Thank you! it was great seeing your pics. ^^
@Gungie no worries and you dont need to thank a random person like me, im just good at
how to use it; i usually do the first row artists and style the middle with (((what you see on the picture) and the last row the extra stuff, like poses, if its a couple or a solo shot and what not (im just doing this for fun); i usually use a tag scraper when i dont know what to generate
Right now this is the BEST furry model that works right out of the BOX, without any kind of special prompting, special tags or embedding, this model save me a lot of TIME as a prompt testing tool. I'm really looking forward for updates for this model. This is a cult classic.
Thank you for the review temp and the pics! ^^ (might have posted this twice)
Details
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.