- Jul 29, 2017
- 14,372
- 186,463
- 1,046
..bruh i swear.....zonies are just dum af.....
..bruh i swear.....zonies are just dum af.....
This isn't true, I occasionally post a clean Dev version without the mods, and the version with the mods gets about twelve times more downloads than the version without. F95 users most definitely prefer the modded version.Mega
This is the actual most recent version of the game from the actual devs making the game. The v2025-07-betavtmod4-0-36.32881 which is currently (5/31) the only available version on the front page is not a stable release, and includes a bunch of mods that many players won't want, or new players will be confused by. Can we please get this correct version put back into the OP?
Not disputing that the modded version is more popular, but in this case correlation certainly doesn't imply causation. People are sheep. How you present something and how accessible it is will often be more important to them than what it includes.This isn't true, I occasionally post a clean Dev version without the mods, and the version with the mods gets about twelve times more downloads than the version without. F95 users most definitely prefer the modded version.
Not in foreseeable future, lol. They're changing the entire event system, so it's almost sure that next few updates will require new saves.Is this remake ever going to achieve save game compatibility? Every little update breaks everything.
EDIT: This is not the latest version of my modded mod, check this post: https://f95zone.to/threads/lab-rats-2-reformulate-v2025-04.32881/post-17293354Here is a snapshot of the img2img version of the GenAI mod (attached zip file), based on version 0.31 (I don't use Discord, so not sure if this is the latest one) I added a few options in the config to switch between img2img and text2img, and to set the denoising strength. The settings I currently use with the DMD2 Real Dream model are this:
View attachment 4814800
I recommend also playing with the denoising strength - a low value like 0.3 will stick more closely to the original graphics/clothing (the ADetailer will still "fix" the face, which can be an improvement) while larger numbers will yield more creative interpretation of the scene/prompt, and possibly more realistic image, but things can also get a bit weird, especially as you get closer to 1 - I would stay below 0.7
Note that the prompt generation is tweaked to work best with img2img, so if you turn img2img off, you might get different results. You can add things to the "Prompt Style" for additional prompting, or edit the python code for more custom prompt construction.
This is still mainly a proof of concept, no a polished product by any means - the prompting needs more work still. Each model has its own optimal settings (sampler, steps, cfg) and handles the prompting differently as well, so its always worth playing around with that if you want different results, but at least this can be a starting point.
There are also situations the mod doesn't handle yet (displaying multiple people at one time ?) and things can also get out of sync when lots of images are being generated in rapid succession, and the wrong image is generated or image skipped/lost. Sometimes generation just stops for me too, and requires a reload (Shift-R in dev mode) and occasionally the game just crashes - not sure if due to bugs in this code, or something else - so beware and YMMV.
Also, model switching from the GenAI mod config screen might not currently work (I commented out some stuff that was giving me issues, but didn't have time to debug) - I use the a1111 Web GUI to switch the model, and just ignore the model in the mod config for now.
Edit: I have been making refinements to the prompting to fix issues that crop up as I play along, so the version attached to the post has been updated to V2 - it's still not perfect, but definitely a lot better, so I recommend upgrading if you are playing along. I have also changed the parameters slightly from above, and now use CFG of 1.5 and denoising strength of 0.6 which seems to work better overall, but feel free to experiment for best results (especially if using different models)
Of course people download your link to the modded version more often than your link to the clean version, when they can just get the most stable clean Dev build in the OP. Well, they used to be able to. I bet if you posted a link to the next AIO stable dev version whenever they release a new one, that would get a hell of a lot more downloads than when you just post the latest beta without mods. I find it extremely hard to believe that the modded version is more popular than the stable dev build.This isn't true, I occasionally post a clean Dev version without the mods, and the version with the mods gets about twelve times more downloads than the version without. F95 users most definitely prefer the modded version.
It's not really a leak, everything is free. But it is very nice for someone to put all those mods together as one package.Personally, I think the Modded version is the superior version of the game, so big thanks to those that leak it and the RL porn clips mod definitely adds a lot to the sex scenes as well, I get that people might not like it real porn in these types of games, but it's mostly done correctly, it will only show the actress faces when it's a blowjob scene for the most part.
And to think that some people complain that developers don't use proper English!..bruh i swear.....zonies are just dum af.....
It's just a colossal undertaking without a convenient method to accomplish it. Renpy can't generate images itself, just load them, so each clothing item has to be fully rendered for every position, every skin color, every body type, etc. Dozens of clothing items, and just unbelievable amounts of effort for relatively minor gain.Hmm tried this a year (two?) or more ago. I remember it was fun, but I wanted to claw my eyes out every time I had to interact with the abominations in the game. I know there was a better graphics mod or other in the works, what's the state of that?
that looks really nice, what gpu / how long it takes to generate on avgThank you so much for this! it worked amazingly, using img2img and a low noise value really does wonders for keeping things appearances consistent and the poses "sane" while still getting some nice improvements.
I figured I'd do my part and help out a bit as well by trying to remove the square background, which proved to be both easier and more annoying than I thought, mostly because the way I started doing it (using the rembg extension) just refused to work, but after I finally switched to another extension instead, it was incredibly simple so now I'm beating myself up over all the hours I wasted working on the wrong solution
View attachment 4895044
I've attached my modified sdcclient_ren.py file, but all I did was literally to add this line to the API-request:
'"script_args": [true, false, false, "#000000", false], "script_name": "abg remover", ' + \
There's no settings to turn it off or anything, so if anyone tries to use this, you have to make sure that the ABG extension is installed.
View attachment 4895045
Very cool ! I spent some time trying to remove the background on python side in renpy, but kept running into issues and eventually gave up.. Didn't even think of doing it on webui side with extensions, will definitely give this a try ! Now I might even feel motivated to try to see how to make the multiple people on the screen at the same time work.Thank you so much for this! it worked amazingly, using img2img and a low noise value really does wonders for keeping things appearances consistent and the poses "sane" while still getting some nice improvements.
I figured I'd do my part and help out a bit as well by trying to remove the square background, which proved to be both easier and more annoying than I thought, mostly because the way I started doing it (using the rembg extension) just refused to work, but after I finally switched to another extension instead, it was incredibly simple so now I'm beating myself up over all the hours I wasted working on the wrong solution
View attachment 4895044
I've attached my modified sdcclient_ren.py file, but all I did was literally to add this line to the API-request:
'"script_args": [true, false, false, "#000000", false], "script_name": "abg remover", ' + \
There's no settings to turn it off or anything, so if anyone tries to use this, you have to make sure that the ABG extension is installed.
View attachment 4895045
If using a Lightning SDXL based model in the Forge fork of webui and a 4090, it takes about 2 seconds to generate each image.that looks really nice, what gpu / how long it takes to generate on avg
Using a 5070Ti, speed varies a lot depending on what model I use and what resolution I want to generate the image in (been trying a bunch of different models and switching between 512x768 & 768x1152 resolutions for the generated image), but I think what I used for the screenshot was somewhere around 10 seconds.that looks really nice, what gpu / how long it takes to generate on avg
What model and params/resolution did you use in the screenshot ?Using a 5070Ti, speed varies a lot depending on what model I use and what resolution I want to generate the image in (been trying a bunch of different models and switching between 512x768 & 768x1152 resolutions for the generated image), but I think what I used for the screenshot was somewhere around 10 seconds.