this is all the beta versions of my Furation models available in FP16 pruned (without EMA) and FULL (FP32 with EMA) flavors, THEY Will have a very basic showcase as-well as ABSOLUTELY NO Commercial use; Besides use on Civitai for some* accessibility.

If the model has (B) it means it seems like the best model so far from my testing. If the model has (F) in the name the model has issues. if the model has (VB) in the name it is the best VPRED model.

Updates about model and what is going on:

Big update, The newest model that I'm working on has hit a temporary plateau, it should be finished after enough models that surpass it in quality are released. But it will be released with more free licensing soon... Once I get some images.

HOW TO USE:

SECTION #1 Prompting:

Prompting for this model is quite versatile but using e621 tags will give you better results, and if you are generating characters use both the old E621 Tags like for example Femboys, You'd need both femboy and girly (Also through my evaluation, I've decided to cut Better hands because the model simply did not need it) which just makes everything better as well as using the negative and positive prompts here:

(masterpiece, highest quality, 16k, high quality, best quality:1.3, highres, digital painting \(artwork\), furry, uploaded_on_e621:1.4), "Put a style like Kemono or realistic here but you can leave it empty",  "WHAT YOU WANT HERE"

And For the Negative prompt I recommend this:

low res, lowres, blurry, bad anatomy, letterbox, deformity, mutilated, malformed, amputee, watermark, signature, unusual anatomy, username, sketch, monochrome, (worst quality:2),(low quality:2),(normal quality:2),((monochrome)),((grayscale)),watermark, blurred, bad face, old, (cub:1.2, child:1.2, young:1.2),bad anatomy,(long body :1.3), BadDream, badyiffymix41, boring_e621_fluffyrock_v4, boring_e621_v4, easynegative, EasyNegativeV2, FastNegativeV2, fluffynegative, negative_hand-neg, ng_deepnegative_v1_75t, NGH, SimpleNegativeV3, updn, <lora:neg4all_bdsqlsz_V3.5:1>

Also Ps, you are going to need the negative embeddings, unless you want bad results.

I have also put all the embeds and Loras in the following link so you guys don't have to get them yourself: https://mega.nz/folder/8y0mFRBT#r2SaP2k-Gm__30AX74JhwQ

SECTION #2 Generation settings:

Higher Steps = better image

Lower CFG = more creative BUT more inaccurate

I suggest you use:

Steps: 40+ for best results, Sampler: DPM++ 2M SDE Heun Karras but DPM++ 2M Karras also works, CFG scale: 10

but if you want you can use:

Steps: 20-28 , Sampler: Euler a, CFG scale: 7

SECTION #3 Upscaling:

Upscaler: R-ESRGAN 4x+ Anime6B (Or really any anime style upscaler), Denoising strength: 0.3,

Also since this page is being used as a beta, I can model dump like how I am doing, without spending hours getting really good images and doing R.N.D and that sort of stuff.

These models are posted here mostly as both a back up for myself and a way for people to see what I am working on. Might make something similar to this for MasterAnime if people post enough images.