Banana Splitz XXL - V1.2.1
Banana XXL 1.1 / Banana V8 / XAVIER / DEEP-COBALT V2
change in prompt adherence to be more like V8
Removed LoRAs that added painterly details in exchange for sharper, cleaner, better anatomy.
Scoring of anatomy adherence: (out of 10 random prompts)
Rate of 5 fingers is 9/10
Rate of bad eyes from a distance is 3/10
Rate of bad eyes with duo is 2/10
Prompt complexity - mild to moderate.
Prompt Adherence - moderate
LoRA compatibility - high.
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
Until 7/18 ONLINE GENERATION REQUIRES YOU TO SELECT A VAE!!!!
Local download patched to 1.2.1
Online generation of patched version goes online next week.
FAQ
Comments (28)
I see your reupload notice, but it still errors with no VAE in the model?
Same, I've already updated, uninstalled and reinstalled everything, but it still says it doesn't include the VAE.
Not sure why comfyui users are running into this
@LatteLeopard Still having this issue in both Forge Neo / Invoke
@LatteLeopard It happens on SDCPP as well
Im going to reupload a complete remerged version sometime today.
You will see a second file for download. do not use BBFINAL.safetensors.
Any plans for Anima? Your model was always one of my favorites. Would be crazy good with Animas consistency.
Furry anima models will require training the e621 datasets before they work properly. It's something being tested. But it's a much much complex and longer process than model merging.
Basically if you see any furry anima models, they just copy they look of an illustrious model without actually understanding the tags
I think anima is much worse than Illustrious/NoobAI. It's very slow.
Anima is SUPER EXPENSIVE
@Owlit You need to tweak the settings a bit. I also was shocked at first, but as soon as I realized, that I dont need a highres fix anymore and do not need many steps for a good image, it changed how I look at it. currently I do 1280x1280 with 14 steps and it works.
Do not treat it like Illustrious. Then it will take ages.
@Owlit I feel the same TBH. its not the level of quality illustrious offers yet.
Any chance to see it for anima model ??
I'd love to see one too, but I think the problem is Anima just wasn't made with very much furry knowledge, since it wasn't trained on any of the e621 datasets, getting a good furry model in Anima will take a lot of actual training. Merging won't save us. We need some rich furries with fat pockets to get in on this. Lmao.
Not getting the VAE issue in reforge, but this model unlike any of my other models is spitting out
TypeError: 'NoneType' object is not iterable
Regardless of what I try to generate which is odd. No issue with the others.
Im going to reupload a complete remerged version sometime today.
You will see a second file for download. do not use BBFINAL.safetensors.
Before leaving a complaint about vae. The local model for 1.2 has vae issues. A complete remerge without touching the vaes will be reuploaded today (7/11/26)
Glad to hear; I haven't been able to get it working with the on-site generator. Thank you :D
@GayPurpleSkunk oh no really? The onsite generator and A1111 was the only way it was working. Also some people can get it working locally if they know how to swap the vae or quickly bake in their own.
if you use the on-site generator you need to select a VAE. This will only be for this week.
@LatteLeopard Got it, thanks <3
ONLINE GENERATION NOW WORKING. REQUIRES YOU TO SELECT A VAE! I WILL FIX THIS NEXT WEEK FOR AUTO.
As an apoIogy for the fucked up 1.2 release I will be releasing a modern remake of V7 + V8 for all the users who loved the pre XXL models. Available next week.
Model is available here. Enjoy!
V7+V8 REMAKE AVAILABLE HERE: "Banana Splitz V8 PRO"
https://civitai.red/models/1922559/latteleopards-private-models
XXL v1.2.1 seemingly has a lower risk of sucking with image mutations than XXL v1.1!
Yeah, that was the reason I had so many issues with the first 1.2 upload. The experimental merge methods I used, accidently deleted a bunch of tensors or something from the vae. (I forget the actual terminal response, but it was something about the vae missing pieces)