This series is focused on women and the female body, in every kind of setting or style. It can do fine art, social media style, surrealism, cinematic, and pornographic very well. The main goal is to have as much diversity as possible in an SDXL checkpoint. Diversity in ethnicity, body type, faces, posing, personality, and locations.
If you like it post your creations!
Donations to my Whop account will exclusively go towards hardware upgrades. Civitai Buzz will be used for site generation and promotions.
Upgrading my local hardware is my on-going goal so I can train locally.
Local training is imperative today. With Ai data centers there will be a vast drain on resources in the areas they operate. Since model & lora training will no doubt be hosted in the new centers, I want to be able to run locally only. The moment my Ai hobby causes actual harm, on any scale, is when I start collecting stamps instead.
General Prompt Guide
Weights in my prompts are primarily for testing the model's capabilities and trying to uncover limitations during test generation. However, I've created the tutorial below to help understand how model weights can be used more effectively.
Positive Attention
Weights between 0.5 & 2.0 are usually sufficient.
I sometimes use weights between 2.0 & 3.0 when I want to force attention to a specific ethnicity for testing.
Higher weights are also helpful when you want to magnify size or specific details. The difference between: large breasts, (large breasts:1.2), & (large breasts:1.8) is obvious.
Recognized weights are usually -5.0 to 5.0 with Dynamic Prompts.
Attention Equation
The parentheses ( ) on their own adds attention weight of 1.1. Unless you specify a weight.
(hyper-realistic) = 1.1
((hyper-realistic)) = 1.21
((hyper-realistic:1.3)) = 1.43
Brackets [ ] are negative attention weight of 0.91, not negative weight, it's just attention that starts under the 1.0 default of all words without weights. Stacking them decreases that number.
[deep shadows] = 0.91
[[deep shadows]] = 0.81
[[[deep shadows]]] = 0.72
Negative Attention
Weights over 3.5 are not usually effective or are a detriment during tokenization.
Negative weights do not have much effect in prompts.
Using too many high weights in the same prompt can cause distortions & deformities.
Using high weights will give specific keywords more attention, but that is often at the expense of other keywords.
Bonus
Prompt with high weights:
(HDR:2.2), cinematic, (natural sunlight:1.23), (hyper-realistic:1.45), (full body shot:0.6), masterpiece, incredible details, [feeling of solitude], mysterious, (deep shadows:0.72), Beautiful (30yo Malaysian woman:2.52), hazel hair, (mid_length grungy hairstyle :1.43), (natural large breasts:1.6), (wearing an unbuttoned stylish silk shirt), (brown pearl g-string, leather lace sandals:1.41), (sexy pose, reclining slightly on elbow:1.68) on a stunning designer wicker couch, at a rustic beach house rooftop with driftwood furniture, seashell decor, a view of the ocean, perfect for casual summer parties, sensual atmosphere, beautiful, guilty pleasure, shot on Canon EOS 5D, RAW.
Prompt without high weights:
(HDR:0.86), cinematic, (natural sunlight:0.8), (hyper-realistic), (full body shot:0.6), masterpiece, incredible details, feeling of solitude, mysterious, (deep shadows:0.72), Beautiful (30yo Malaysian woman:1.32), hazel hair, (mid_length grungy hairstyle), (natural large breasts), (wearing an unbuttoned stylish silk shirt), (brown pearl g-string, leather lace sandals), (sexy pose, reclining slightly on elbow:1.12) on a stunning designer wicker couch, at a rustic beach house rooftop with driftwood furniture, seashell decor, a view of the ocean, perfect for casual summer parties, sensual atmosphere, beautiful, guilty pleasure, shot on Canon EOS 5D, RAW.
To force clip & vae in FP32
Forge:
./webui.sh --clip-in-fp32 --vae-in-fp32 --no-half-vae(or add the commands to your webui-user.bat (Windows) or webui-user.sh (Linux) in
COMMANDLINE_ARGS= --clip-in-fp32 --vae-in-fp32 --no-half-vaeFor all commands (many are obsolete now since the developers have made them default)
Comfy:
python main.py --fp32-text-enc --fp32-vaeI don't use Comfy, so this is what I've seen on the web. Here is a link to all commands:
https://gist.github.com/ravetank/cedcd1ea89738b2e79b9f01e45a1a03d#file-comfyuihelp-txt
Description
Settings I use:
DPM++ 3M SDE karras
45 Steps
3.5 CFG
FAQ
Comments (5)
Crazy that Reality BoundXL Feisty v16 and Intrepid XL v6.0 both turned out at exactly 6,938,041,648 bytes. Had to run a hash check on them just to make sure I didn't grab the same file twice or that you weren't messing with us or uploaded the wrong thing (only tested Intrepid so far). That'd be funny though, cause I'd probably still pick out random things I like with one over the other even if they were the same! XD
Ha! Nah, I wouldn't upload the same checkpoint. It's my method of merging & usage of custom seed models. I have different types of over 2 dozen seed models that are meant to enrich each series with separate data. Which are themselves rotated & created with new data on a weekly basis. Mad scientist levels of model enriching ;)
I just wanted to report that using V15 with the DMD2 lora and Euler A yields fantastic results for me. I haven't tried this combination with earlier models, but it did not work nearly as well with the newer V16 (which works fine with DMD and LCM).
I've considered making DMD versions. But I figured people can use the lora if they wanted to. I'm biased against it because I often notice muted colors & less unique faces on some models. Thanks for letting everyone know. :)
Well, gooners like me often just want to make more "good" pictures quickly and may be willing settle for less than the great imagery your models are capable of. But the point I wanted to emphasize was the performance of Eular A combined with DMD with this particular version of Reality Bound. With most models, LCM is the only sampler that works well with DMD (whether built in or by Lora). While Euler A does better than most other common samplers with DMD, it usually produces artifacts or excessive, unwanted detail, and that's true in other RB models I've tried it with. But RB v15 is different. I don't know what made me even try using Euler A with v15, but it worked as well or even better than LCM with that model.