Hotscreen

Add very hot effects to your screen. · By PerfectFox265

Add to collection

game Community Devlog

Hotscreen community

Mod to generate the description of censored content with an LLM Sticky

A topic by PerfectFox265 created Oct 26, 2025 Views: 6,912 Replies: 14

Viewing posts 1 to 10

PerfectFox265Developer131 days ago (9 edits) (+4)

I've create a custom box scene that uses a LLM loaded in LM Studio to generate a description of the hidden content.

Video showcase using images by MIAOKA on civitai :

How to use it

1) Download the file "llm_description.box.tscn" here or here and put it inside your CUSTOM_DATA folder.

2) Start LM Studio. (You can install it from here : https://lmstudio.ai)

Install and load a vision model. (lmf2-vl is fast. qwen2.5-vl-nsfw can allow spicy descriptions.)

Start the server. (*)

3) Start Hotscreen.

Add a filter -> Mods -> Box scene

Edit filter -> Select custom scene -> Open the file "llm_description.box.tscn"

The "mod" is very simple. It's only a text file loaded like a box. It doesn't reference any Hotscreen scripts/variables, making it easy to modify in Godot (or by an AI chatbot). There are variables at the top to change the prompt, color, etc.

I think this mod illustrates the power of Hotscreen's modding capabilities well. I hope you will find it cool too. 😊

(*) Here are my settings in LM Studio which should be the default ones :

PerfectFox265Developer unlisted this topic 131 days ago

PerfectFox265Developer relisted this topic 131 days ago

HotpointUser131 days ago (1 edit) (+1)

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?

PerfectFox265Developer131 days ago

You can modify the prompt at the top of the file.

HotpointUser131 days ago (3 edits)

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?

PerfectFox265Developer130 days ago

You have to restart Hotscreen after you modify a .tscn file to refresh the changes. So your font size should be bigger next time.

The image send to LM Studio is obtain in the function get_screen_image_under_box() (line 84). You can easily modify it.

The system prompt ("You are a helpful assistant.") and settings (temperature : 0.8, max_tokens : 500) is sent with your prompt (line 117). I think this overrides the settings of LM Studio.

HotpointUser130 days ago (1 edit)

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)

PerfectFox265Developer129 days ago

The vision model usually have VL in their name. Qwen3-VL should be available in LM Studio this week.

It would be also possible to finetune a model with this : https://github.com/unslothai/unsloth using their pre-made google colab. We just have to create a dataset of example of images with their "censored description".

kuiluic130 days ago(+1)

good idea😊

psi-conaut130 days ago(+1)

The software crashes when I turn on the mod.

mementum128 days ago

I tried both of the vl models you suggested, but with the nsfw one I still get censored text results. Tried diffrent prompts but couldn't do it

Generic Gio62 days ago

This has been very interesting to observe. I have used this decently. My only complaints are that the Qwen 3 model seems to be rather restricted in it's usage. It gives me very bland and disappointing responses. You ask it to call you one name, and it goes on a superman rant about peace and justice (harmlessness etc). Do you have any suggestions? It is a very good feature integration, I just need a better model it seems. My goal stems not from the description, but from getting implicational second person statements towards the reader (me).

PerfectFox265Developer60 days ago

For now, the best would be to finetune an uncensored Qwen3-vl model. There are pre-made google collab to easily do this, but it is required to create a dataset of images with their expected spicy description.

downer2827 days ago(+1)

Just want to say thanks for creating this mod!

I played around with this for a few hours and just wanted to offer some tips. First of all, the best model to use for this is joycaption beta one. It is built specifically for NSFW descriptions and works great. Second, change the var update_description_every in the mod file to a higher number, like 30 seconds. That will ensure it only generates descriptions every 30 seconds. Also, change the cooldown on the mod in hotscreen to 30 seconds so that when the detected area goes in and out of focus it isn't trying to generate new descriptions every time. You can alter the font and colors in the mod file like I did too. I just made the background opaque so the censorship was visible.

I'm using the following prompt for covered breasts:

"This is the scenario: You are a mean, bratty girl who is describing a woman's breasts the viewer is watching. The breasts are censored, so the viewer cannot see any details. So, the girl teases the viewer when describing the woman's breasts. She should always tell the viewer the cup size of the tits. Refer to breasts using one of these words: boobs, breasts, tits, titties. Refer to the viewer using one of these words: beta, loser, bitch boy, gooner, pussy-free beta. The viewer knows that he doesn't deserve to look at women's breasts. Omit the words image, photo, or photograph. Be generous with adjectives to describe the woman's breasts. Be generous with cuss words like fuck, fucking, shit, bitch. Short and concise, limited to two sentences only!"

You will need separate prompts for other body parts, especially nudity, but it's a good framework to start. It's hard getting the prompt to give you the output you want, but just keep trying different things.

Here is an example of the output:

HotpointUser26 days ago

It seems like the file name has changed. l2fgsh? Is that new filename for it? It's not being detected when I put it in the folder. I remember I got this to work a couple months ago but I'm having trouble now.

Jannich0223 days ago(+2)(-1)

Hello PerfectFox265 Hotscreen is werry good but are you able to make a black out mood that black out the female body like this picture.

itch.io

Hotscreen

Mod to generate the description of censored content with an LLM Sticky

How to use it