V4.3_EXP released...
This is based on realism and currently is under testing... More images will be uploaded later... V5 will come soon for more underrepresented concepts..
Strength: 0.8 -> 1 -> 1.2 -> 2
It's my first trained LORA based on KREA 2
V4.1 RELEASED!!
Better prompt adherance. FAR FAR BETTER realistic skins. Face expressions are here. Most things are better..
Things bad:
- Masturbation concept not defined completely
- Sometimes strange artifacts can come like in 2:3 you want a sexual image that requires width then change to 3:2...
- for censored (Asian JV), increase strength by 0.1 and try 1-2 times.
- feedback welcome as always, gonna upload more images.
V4:
Will be released in 1-2 days, one of my friends gave me access to his h100.. This time will work on better prompt adherence and get few issues resolved.
If getting weaker results then use strength of 1.5 or 2.
V3 Released!!!:
strength: 1-1.5
for jav use 1.2-1.5 so mosaic doesn't come.
Added: Asians, Blacks, realistic skins etc... (use to know better)
Recommendation use: https://huggingface.co/Beinsezii/Krea-2-Turbo-Projector-Scale-LoRA-Diffusers for better control with 0.01 (but it takes hit on quality just a little)
For better prompt adherence, increase strength a little of the second lora...
also, don't just write a thick cock between or somewhere.. write like a man then his cock so it understands.
Prompt adherence can be a hassle please use the above lora (0.01 weight) and next time I will try to make it better. V4 will take some time since gathering dataset, 200+images with 5k steps and training took a while and lots of cash from me, trained with RTX 6000 Pro.. Please give feedback since I am learning...
V3:
Will be out within 1-2 days, gotta arrange those gpus. Also, i got a massive uhd dataset i found somewhere, so this version should be most realistic and the best version.
TO BE FIXED:
- Mosaic Issues sometimes
- Asians to be added
- Blacks enhanced
- Better skin (sometimes skin looks plasticy)
V2 OUT:
Recommended:
- Strength: 1-1.5
- Do NOT USE conditioning node as it seems to be degrading the quality with the lora.
New Features:
Better SKIN, no need for KNP trigger TAG.
Added:
Detailed Pussy
Detailed Assholes
Different Poses
Different undressing styles
Male Cock
Sex (Basic)
Cowboy etc...
More things to come especially sex styles and art loras soon but :( it took 5 dollars to make this...
Please give Feedback.
Description
This drastically improves realism and adds few concepts...
Note: This is in experimentation... more versions to come soon...
Prompt Guide:
The Golden Rule: Do not over-prompt. Word salad confuses the model. Write in short, punchy, flowing sentences. Let the LoRA do the heavy lifting.
1. The Core Formula
Use this exact sentence structure for the best results:
[Camera Angle] + [Action/Subject] + [Explicit Detail/Fluids] + [Lighting/Camera] + "very realistic"
2. The 5 Rules of Raw Realism
Rule 1: Geometric Angles (NO POV). POV shots result in floating limbs and missing bodies. Always use full-body geometric framing:
wide side profile shot,45-degree front angle,overhead high angle looking down, orlow angle side shot. Addfull bodies visible.Rule 2: Cheap Cameras & Bad Lighting. Never use "8k", "masterpiece", or "cinematic lighting". Use
cheap smartphone camera,35mm film grain,cheap point-and-shoot camera, or90s camcorder still frame. For lighting, useharsh direct flash,blown-out highlights, anddeep harsh shadows.Rule 3: Explicit Anatomy & Natural Hair. The AI will default to hairless, sanitized bodies. You must explicitly command natural body hair:
completely natural, untrimmed bush,wild, thick black pubic hair. Use crude tokens (pussy,cock,cum,asshole) because that is what the LoRA was trained on.Rule 4: Literal Actions & Messy Fluids. Don't hint at actions. Say
thick cum flowing down to her asshole,thick white cum bubbling out of her hairy pussy, orthick ropes of cum flying out of his cock.Rule 5: Gorgeous + Gritty Contrast. Pair
breathtakingly gorgeoussubjects withmessy,dirty, orgrittyenvironments.
3. Handling Multiple Subjects
If you are generating 2+ women, the AI will clone their faces. You must define them individually using the "The first is... The second is..." structure.
Example: "The first is a pale blonde with high cheekbones. The second is a curvy Latina with a mole on her thigh."