Banana Splitz XXL - V1.1
(Banana XXL + FurrySpec | Simple Furry Mix + ReKemonoV9 + Furry Dreams + a few LoRAs )
Minor change in prompt adherence
style update - slightly more painterly and lite 2.5D aesthetic.
Prompt adherence slightly LESS sensitive (allows for more advanced prompting)
Camera angles and poses are about the same.
Banana Splitz XXL - V1.0
(Banana V9 + FurrySpec | Simple Furry Mix + DeepNavyV3+ ReKemonoV7)
Minor update to coloring + lighting
Major style update - smoother, cleaner, less painterly more solid.
Prompt adherence slightly more sensitive.
Offers a high quality 2D - 2.5D look with expressive posing and faces.
Camera angles are more creative when propmting for dynamic angles.
Banana Splitz - V9.0
(Banana V8 + V6)+DeepNavyV3+Luno V6[Renamed ReKemono])
Major update to coloring, lighting, poses, camera angles.
LoRa compatibility is still great
Minor clip difference from 8.0 (adherence is roughly the same)
Banana Splitz - V8.0
(Banana V6+V7a+V3)+DeepNavyV3+Hyphoria+More)
Major clip update. Expanded clip with Hyphoria
which is a model that cleverly merged 10 different models clips
Rule 34 Data set added as usual.
Prompt adherence is crazy strong.
LoRA compatability is also very high.
Backgrounds are wildly beautiful.
Can do humans/Anime with no problem.
Extremely large spectrum of styles can be prompted.
You can combine artist tags easier like in the SD1.4 days
_______________________________________________________________________
Banana Splitz - V7.0 Side B
This is basically V7 but with a more westernized toon style
(Banana V6+V7+V5(ReMerge)+DeepNavyV3+Oops All Toons)
LoRA Used:
KSM - Gives the model a more bit of western toon appearance. Helps with artist tags
Dirtysoda - Another LoRA for helping westernize this model more
Rule 34 Dataset LoRA - Smallest ammount used for activation. This is for better LoRA compatibility and higher usage causes noise. To finetune the R34 Lora within this model, please use actual Rule34 Lora. (READ INSTURCTIONS)
https://civarchive.com/models/1191424/pornmaster-rule-34-prompts-illustrious-and-noob
__________________________________________________________________________________________________
Banana Splitz - V7.0 Side A
(Banana Mix+MolKun-Mashup+Luno Mix)
Banana Splitz XL 6.0 + Banana Splitz 5.0
Other models in recipe
Hyphoria
Nlxl:
Nlxl v0.9 is a checkpoint that produces more stable and detailed results through enhanced Model Merged checkpoints created through model merging, combining the natural image generation capabilities of Illustrious, the extensive dataset of Noob, and the unique strengths of different models depending on the version
_______________________________________________________________________
Merged LoRA info, so you know how much extra of the same lora to use, or if it lora's wont be compatable. Also lets you know whathey do.
KSM - Gives the model a more bit of western toon appearance. Helps with artist tags
Rule 34 Dataset (LoRA)
The developer speaks Chinese only and doesnt really reply correctly to anyone.
but this LoRA adds a large amount of tags that do not exist on danbooru or e621
This creates an effect that allow an awesome solid mix of tags/natural langauge.
It also makes NSFW content so much better. I think it also re-enforces the knowledge of already know tags for pose, expression and anatomy wise.
bruhhhh Its such a huge an potent lora. Its 3.4gb and is merged is sometimes merged in SUB 0.1 weights. like 0.08, 0.06. Its gonna be doing something powerful
__________________________________________________________________________________________________
Banana Splitz - V6.0
(Banana+Oat+Sudachi Mix)
-Banana Splitz XL 2.0 & 4.0 mix
-Sudachi XL
-Plant Milk - OAT
-Xavier-Shift (Trunk of Furry Junk)
-Mol_Kuen DeepNavy
_______________________________________________________________________
Banana Splitz - V6.0 BETA
(Banana-Hassaku+Walnut Mix)
***NOTE V3.0 AND UP IS FOR EULER A SAMPLER ONLY**
New base merge recipe:
-Banana Splitz XL 3.0 & 5.0 mix
-Sudachi XL
-Plant Milk - Walnut
-Hassaku 3.0
-Mol_Kuen DeepNavy
-Hyphoria
-Rule34 Prompt Lora updated to V2.0
__________________________________________________________________________________________________
Banana Splitz - V5.0 [ READ ME! ]
(Banana-Hemp+Walnut Mix)
***NOTE V3.0 AND UP IS FOR EULER A SAMPLER ONLY***
Try using a CFG Rescale plugin for ComfyUI or A1111 if want to attempt another sampler
New base merge recipe:
-Banana Splitz XL 2.0 & 4.0 mix
-Sudachi XL
-Plant Milk - Hemp ll
-Mol_Kuen DeepNavy
-Rule34 Prompt Lora updated to V2.0
TEXT ENCODER MODIFICATION:
This version will properly acknowledge prompting from those who write longer and wildly detailed prompts. BUT! it will also help/support simple prompts into creative works of art!
Great for beginners and fantastic for pros to push their creative limits!
Positives for the Pros!
highly specific prompting will now have a much higher chance to affect small details.
I suggest even putting weather or time of day (morning, golden hour, night).
Even objects in background like a swing on a tree or a bookshelf indoors.
Style/Artist blending can have surgical precision.
detailed negative prompting can help shape result moderately better too
Positives for everyone!
Simple prompts will have a boost too:
Short or vague prompting will give creative wildcard like behavior.
Can give good solid and creative prompts with simplistic prompting.
Good for beginners to help build upon their prompts making them more verbose and gaining the skill to write more detailed prompts.
Great for beginners to see the changes by adding, changing how they prompt.
Remember! Everyone prompts differently and this model can certainly help you tone up on your own prompting skills!
_______________________________________________________________________
Banana Splitz - V4.0
(Banana-Walnut Version)
New base merge recipe:
-Banana Splitz XL 2.0
-Plant Milk - Walnut
-Sudachi XL
-Rule 34 Dataset V1.0
-Style is mostly the same, but higher quality.
-More detailed backgrounds
-Prompt adherence is average. Needs work.
-Extremely LoRA compatible
-Artist styles absolutely SHINE on here.
-Can one-shot generate a good image 3/4th of the time
_______________________________________________________________________
Banana Splitz - V3.0
(Banana Flax Daquiri Mix)
A 'high-quality' Western-Kemono hybrid with crisp linework, soft but dimensional shading, and a balanced 2.5D aesthetic.
Better and easier prompt adherence
Clean, stylish, thick lines with glossy 2.5D textures
Contains Rule 34 Dataset.
Great eyes! Great Fingers, Awesome poses.
Check out this amazing finetune of Banana Splitz by LS582.
Fifth Mix - Banana Daquiri does exactly what its told, clean, crisp style. This is what ChromaXL should have been IMO.
If you like this model try it out!
_______________________________________________________________________
Banana Splitz - v2.0
(Banana Daquiri Mix)Updates:
-Moderate Style Change
Model now is has moderately higher saturation, slightly lower contrast, more colorful.
Less flat and washed out (if you like that look from V1 I may consider making a V1.X, Plz Comment)
When no style is specified you will get random styles beetween 2.5D cartoon and 2.5D semi-photorealstic
-Massively Improved prompt adherence.
Has improved natural language understanding(needs to be mixed still with tags)
Prompt this model like a combo of Fifth Mix - Banana Daiquiri and NoobAI
-Refined quality and body comp.
Much less random zoom ins and cropping when using "close up" tags
You can get good eyes on raw gens 60% of the time with full body/multi character
You can get good eyes on raw gens 95% of the time with portrait/close up/solo
Different male and female body types
better knowledge of animal dicks and pussies(specifically canine)
-Pure NoobAI cyberfix, train difference injection
Use e621 tags for artist associated with NoobAI
vast knowledge of furry artists and can nail the style very closely 80% of the time. (check last 3 images in example images)
Natural Langauge is better understood. but not perfected.
-Making Lora/Lyrcoris models use the following.
NoobAI EPS1.1
Illustrious V0.1
WAI-NSFW-Illustrious V11 (Smooth looking with mild risk of sucking)
Fifth Mix Or Banana Splitz (Highly creative / Lower risk of sucking, but makes it useable for these models only)
__________________________________________________________________________________________________
Banana Splitz - v1.0
(The Original Banana Splitz Mix)
ORIGINAL VERSION 1 MERGE DETAILS:
Models used:
Fifth Mix
FurryToonMix
MolKun Mix
NoobAI CyberFix EPS V1.1
Custom Oops! All Furries
(Re-Merge/Pruned All trace of models that use ChromaXL Or ChromaMorgy
Custom Indigo NoobAI Mix(I might release this)
Custom Nova Furry Mix
(Custom Add Diff/Train Diff Mix of 3 versions - Might release this too)
Hassaku V2.1
Interested In any of the custom models used?
Let me know!
Description
Added Rule 34 dataset
Updated to ILX 2.0
Better Prompt Adherence.
More detail in backgrounds
Cleaner style, less blotchy.
Slightly more 2.5Dish
FAQ
Comments (22)
Version three is great! It managed to do well despite that I don't remember how to properly prompt Illustrious models, artist tags work as expected, this model is just a fun time to work with, highly recommend anyone reading this to try it! ❤️
Thanks! I really appreciate the review.
If you need help, this is how you start your average prompt for this model.
(Also for all non-pony SDXL models)
masterpiece, best quality, newest, absurdres, highres, anthro
The more quality tags you add the more 2.5D it will begin to get
Example of other quality tags:
2024,
very awa, (I guess this tag is used alot on danbooru, so it makes the image kemono)
very aesthetic,
8k,
ultra-HD,
Heres some of my favorites ive seen others use on my images, the changes are mild, but definitely notable.
[Painterly 2.5]
masterpiece, ultra-HD, impressionism, high detail, depth of field, dynamic lighting, best quality, very aesthetic, 8k, best quality, anthro,
[Vivid, Shiny, extremely detailed 2.5D]
masterpiece, high quality, absurdres, newest, 2024, stabilized, amazing quality, 8K, perfect quality, best quality, absolutely eye-catching, ambient occlusion, raytracing, good quality, very aesthetic, absurdres, newest, depth of field, focused subject,
@LatteLeopard Oh I see! Then I suppose it isn't that different from NAI models. Also thank you for your detailed response! ❤️
Normally I refrain from using tags like '8K' or 'absurdres' because they'd make the image look more 3D, at least in my experience. But if I understand you right that's not the case for this model?
@Zachisalreadytaken not too sure. But it sounds very likely those tage cause 2.5d art
V3 looks solid, great job on release!
Amazing, if V2 was an already near perfect in prompt adherence matters, V3 just make everything even more great, almost every pose, angle, environment and characters worked as a charm
Thanks for your work and keep going forward! ❤️❤️❤️
There seems to be an issue, I can’t use V3, only V2, is something wrong or am I just stupid? (Mobile user btw)
It wont be available for online generation until tomorrow night after auctions end. People can bid for a model to get a spot in the 200 slots available for online generation. 3.0 will win a spot this week no issue.
@LatteLeopard Oh ok, thanks bud!
Can you make V2 available to use, i liked the look of that model
I personally will only place bids on the newest version(I put down 30,000 - 50,000 buzz weekly). But you can help bid on it with any other users who will want to use it.
How do I prompt artist tags? Does it require "artist:" or "by"?
Just the artist name is needed
Search for the e621 artist dataset from NoobAI, there is a csv where you have the exact trigger word and the count of images it has on their e621 tag page (bigger numbers will bring outputs more closer to the artist style)
Well on e6AI, they’re called directors. Sounds about right.
When next update. This model is already absolute cinnamon, but I’m just curious when the next ones coming. I have 0 idea on how to make a Lora or Model, so, just another question, how long does making/uploading a model take? Thanks. Once again, excellent model you’ve made.
So models like NoobAI, Hassaku and RouWei are checkpoint trained models. These train aditional data ontop of Illustrious and take days.
Models like mine, Nova furry, YiffyMix are checkpoint merges. That means we are merging the model weights. This is quicker to accomplish but requires alot of testing to get what you need.
Loras are more effort to train than model merges, but not as intense as trained models.
Loras can be trained in an hour.
Think of it like this.
Checkpoint Trained models are like big updates to a game
Model Merges are like texture packs
and Loras are like mods.
@LatteLeopard OOOOOOHHH I get it…
Does it work with meta tags other than quality tags (e.g. source mismatch, bad id, etc.)?
Thank you very much, it is very versatile. Congratulations.
As the Civitai Model Journalist, This is one of the more higher quality furry-esque models, I’ve used, no matter the prompt, sampler, and LoRA’s, even good at humans! only bad thing is that is quite really doesn’t listen to things about darker colours (for me personally)
You did good on this mate, I expect a wonderous amount of quality from future models just like this one. And this is probably your Magnum Opus (unless you make one better than this, then I’ll be darned)
10 Irish Mercenaries out of 10 NCR Mojave Rangers!
Thank you!
I will fix the contrast for V4
Also check out my new model Stormtooth XL, if you like semi-realism, this is real treat.