Model Information





Description
Winnougan Presents: Toilet Tunes Turbo for Krea 2

A special finetune including my secret cache of LoRAs trained on an RTX 4090.
As with all models, expect all quants: INT8 Covnrot, INT4 Convrot, FP8, MXPF8, BF16, NVFP4 and GGUF.
Settings and Workflow:
This is a Krea 2 Turbo finetune. It does all things NSFW, but will do SFW if you want it to. It shouldn't be your go-to SFW model though, since it's got a hair trigger for the dark side.
I prefer to use ER_SDE and Beta 57. 8-9 Steps. CFG 1. To use my workflow you can grab it here.
Consider supporting me on Ko-fi. Even $3 goes a long way!
I'm burning through resources, electricity bills and shaking with fear if anything should happen to my ram sticks or SSDs in this alternate reality where ram costs more than a G-Wagon.
All quants converted with the help of Starnodes: https://github.com/Starnodes2024/comfyui-starnodes-modelconverter
All workflow contains Starnodes nodes: https://github.com/Starnodes2024/ComfyUI_StarNodes
ππ»ππΎSupport me below ππΏππΌ
π Workflow: (https://pastebin.com/nHWpSccV)
π Support on Ko-fi: (https://ko-fi.com/winnougan)
I'm saving toward a hardware upgrade so I can expand into Ideogram 4 and LTX-2.3 video LoRAs and deliver releases faster. Every coffee helps make it happen. β
π€ YouTube β Tutorials and reviews: https://www.youtube.com/@Winnougan
π Discord β Releases, requests, and conversation: https://discord.gg/CJv5wceJaN
Toilet Tunes Turbo V1.0
Model Details
- Type
- AI Model
- Task
- text-to-image
- Subtype
- Safetensors / Checkpoint AI Model
- Created
- Updated
- July 17, 2026