A merge designed for generating good results from NSFW concept LoRAs. From my observations, concept LoRAs improve with training data from multiple mediums. So the goal of this mix is to blend mediums like anime, artistic, and realistic, but ultimately lean towards realism for output.
I personally use this model to test out my XL LoRAs. I don't feel it's as good as the original yet, but I can't keep posting my LoRAs without sharing my base for you all to test the prompts with 😜.
Generating
I found the best results were starting with 864x1152, clip skip 1, cfg 7, DPM3++ SDE Karras. Then img2img: resize by 1.5x, denoise 0.3, Script: SD Upscale -> R-ESRGAN 4x+ @ scale factor 2. (this eats up 24gb of vram for me).
No refiner is needed.
Prompts
Suggested general prompt:
detailed background, masterpiece, best quality, high quality, highres, absurdres, award-winning, professional, highly detailed
Negative prompt: FastNegativeV2
Suggested realistic prompt:
8k, highly detailed, ultra realistic
Negative prompt: cartoon, 3d render
Resources
Overall, this model is currently a merge of: Spectrum, Dynavision, Juggernaut, Explicit Freedom, Realistic Freedom, Gleipnir, All-in-One NSWF LoRA.
Caveats
Specifying any kind of breast size will likely generate nudity.
Specifying a hair color or facial features will make the results more human (though this may be what you want)
It has a slight watermark bias due to the merging of some NSFW LoRAs. If you're using LoRAs that tend to generate them, you can add "watermark" and "signature" to the negative prompt.
Description
FAQ
Comments (5)
this looks promising, considering the sample images and the merges listed. thanks for this, will be trying it out.
Are those samples loras? Because i cant get any animal hooman out of it
Those are from the base model, but you'll definitely get way better results from using loras. For the base model alone, try starting with "ANIMAL woman hybrid" or "ANIMAL creature", then add in human-like attributes. Adding in things like hair color, eye color, clothes, hands, feet, shoes tends to remove animal attributes.
I've had the same problem - you can see it in my posted images. I've tried the same kind of things NSFW mentioned, but it's definitely a struggle for it, right now. It does much better for non-furry stuff, but even with scales I had some trouble - at least when it came to transformation style prompts (which work in Fenris, so was hoping it would have carried over here, but it is two merges removed). A bit more luck if you can push it into drawn/anime, but even that I sometimes had to push for through adding "photorealistic" i nthe negative.
NSFW - any chance of baking in your XL Loras so far into the model? They've been promising! And I'd suggest a direct inclusion of FenrisXL for better transformation support. Gleipnir is good but its bit more all-purpose.
It's been so long. Welcome back. Was wondering when there would be an update to Transformix!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.