itch.io

It would be nice if the 'Detect only on a custom area of the screen' function worked for the inverted boxes as well so I can stop it from censoring the tabs as well.

I changed the Var Prompt to "Response should consist of only a description of breasts visible. Describe the shape and size of the breasts in as much detail as possible. Maintain anatomical correctness and accuracy. Try to accurately state the bra size of the breasts. Describe the color and size of the nipples. Don't use the words [style, image, close-up]." I also created a system prompt in LM Studio to say the exact same thing. It still gives varied descriptions of things in the image besides the breasts but it's a cool feature and kind of works.
Doesn't work so much on videos because of the flashing censor detecting undetecting and not having time to load the description.

I'm going to experiment with different LLM engines. (EDIT: I don't know how to specifically search for models that can do image detection, little yellow eyeball)

That works well and a very nice feature. Anyway to increase the font size? I tried changing  var custom_font_size: int = 30 but it didn't increase the font size. 

Does it see the whole image and only describe what's in the box or does it only see what's in the box?

Would it help to add a prompt or system setting in the LM Studio program to assist w/ the description or response it writes?

That is very cool. I will try it. how can we modify it so it describes it in certain ways. Such as mentioning breast size?

Would be nice if the pixel slider bar was bigger or had a field to enter the exact #. It is hard to get precise. Maybe increase font size too. Thank you.

Yes Detect Small body parts on widescreen was enabled. I think it was just one time, I'm not sure. I'll mention it again if it notice it or it starts bothering me.

Don't mean to send you on a wild goose chase but I am seeing boxes work on thumbnails and then when enlarged it's no longer censoring it.

Specifically for me it's the reveal area censor function. 

Some detections don't work in full-screen unless I turn off detect small bodyparts x4

Maybe the levels detection area should go into each level. So you can customize what causes the progress bar to progress at each level. For example level 1 shows boobs. Level 2 blocks boobs so boobs so in level 2 boobs no longer progresses the bar.

Edit: It seems like the Decreasing Progression Speed overpowers the Increasing progression no matter what number it's on. Even. 0.01 overpowers the increase if there's both a box that is supposed to increase the progression and decrease the progression at the same time.

Just wanted to say I have no idea how mods work or where to even begin. It must be some advanced stuff as the changelog mentions APIs. It's ok but was curious if people will post their own unique setups to copy. Thanks.

me too

I just used one of the models and it seems to be better. I do have a high resolution on my monitor. 

Just want to add so I don't create a whole new thread. I like inverted boxes, but HotScreen should stay on top so we can still make changes. Also can't navigate other stuff if it's full black screen and you go to a non-porn page.

Uses massive memory and slows everything down. PC becomes unusable. Even after closing Hotscreen I can't open my Task Manager.

Hotscreen using profile : default

Hotscreen Overlay starting at Max FPS : 59

Translations added from ./custom_ressources/translations.csv — languages : ["en", "zh", "es", "fr", "ar", "ru", "pt", "ko", "ja", "de"]

Using saved language code : en

Windows version : Microsoft Windows NT 10.0.26100.0

CPU : 13th Gen Intel(R) Core(TM) i5-13600K, Cores : 14, Threads : 20, Max clock : 3500 MHz

Using video adapter : NVIDIA GeForce RTX 4070 from NVIDIA type DiscreteGpu

Driver infos : d3d12 version 12_0 api 12_0

Adapter 0 NVIDIA GeForce RTX 4070

Screen Rect 0 : Rect { X = 0, Y = 0, Width = 3840, Height = 2160, Top = 0, Bottom = 2160, Left = 0, Right = 3840, Location = Point { X = 0, Y = 0 }, Size = Size { Width = 3840, Height = 2160 }, TopLeft = Point { X = 0, Y = 0 }, BottomRight = Point { X = 3840, Y = 2160 } } Orientation : 1

Adapter 1 Microsoft Basic Render Driver

Starting Screen Recorder

DXGI initiated with a resolution of 3840 x 2160

DXGI using Video card 0 and monitor 0

Max FPS Record start at 59

Hotscreen version : Windows - Full version - v0.6

Max FPS of Overlay set to 59

Frame Latency of screen set to 2

MaxFPSRecord at 59

Avx is supported.

Detection starting using model : ./models/hs-real-y11n-320-fp16.onnx

Detection starting using eye model : ./models/eyes-detection-01.onnx

Detection starting using device : 0

Max FPS Detection start at 59

Use double Detection start at True

Update time of eyes detection start at 0.24

Setting MaxFPSDetection at 59

Max FPS of Overlay set to 59

MaxFPSRecord at 29

Setting MaxFPSDetection at 29

Max FPS of Overlay set to 59

MaxFPSRecord at 59

Setting MaxFPSDetection at 59

Recording is too slow. Stopping screen latency.

Closing...

Screen recorder thread ends correctly.

Thanks. I just modified Safe for Beta, I think it's the same thing.

How do you add Level 2 to the Levels Collection? Also the 'Transitions' drop down doesn't show anything.