Jump to content
The Dark Mod Forums

Zerg Rush

Member
  • Posts

    1029
  • Joined

  • Last visited

  • Days Won

    17

Posts posted by Zerg Rush

  1. Quote

    Infinigen is a procedural generator of 3D scenes, developed by Princeton Vision & Learning Lab. Infinigen is optimized for computer vision research and generates diverse high-quality 3D training data. Infinigen is based on Blender and is free and open-source (BSD 3-Clause License). Infinigen is being actively developed to expand its capabilities and coverage. Everyone is welcome to contribute.

    https://infinigen.org

    https://github.com/princeton-vl/infinigen

  2. I have assumed that, although there are models made, it is not a simple copy - paste, independent if it is from these repositories or stolen from other games. Regarding AI, it can be a good tool for certain assets, bad only if it is used as a shortcut to create a game and not just as another design tool. The AI tool listed, although it can be create other things, can be used very well to quickly create textures, for example, saving time in the game developement. AI also can be used to create classical paintings, much used in TDM, without any copyright problems, things like this, and maybe even better adapt to the plot as the same paintings used since several Years now, apart of the one I made for the Black Mage.

    It is clear that stealing designs from other creators is very ugly and certainly a bad path, which is why I have said that piracy is not necessary, with the free and open-use resources available. You surely have other sources of these, apart from the list What I put.

  3. 16 hours ago, fortuni said:

    Thanks, already had the those, but had spent half an hour trying to work out how to open the doors to the big cage to get to the control panel inside. Assumed it was another mini puzzle. 

    Spoiler

    You can only reach some things on the table behind the fence

     

  4. 11 hours ago, Xolvix said:

    Krita has really gone from strength to strength in the last few years. Even though it's targeted more at painting, I'm finding Krita functions well even with general image manipulation to the point where it can replace GIMP for most tasks for me. GIMP is still handy at times but Krita's UI is superior. I did try a simple AI diffusion plugin I found for GIMP but it did all the work on a server on the Internet somewhere and that required being put in a queue, etc. My card is powerful enough to do the CUDA work locally with this Krita plugin, and after some practice it's really effective.

    Yes, Krita is in first line for paintings, but at professional level. The only alternative  is Project Dogwaffle (Howler), but it's proprietary paid soft (latest in offer $14.99), well, (very) old versión downloadable released as freeware *

    * Screenshot freeware version (Windows only)

    GsxYH6XCe3u78B8uLGoRS.jpg.

  5. 10 hours ago, datiswous said:

    Interesting, didn't know this yet. Problem is that tutorials for Blender won't work with that well, so although maybe it's easier to use, I'm not sure if it's a better choice.

    Try it, its FOSS like Blender, noyhing to lose.

  6. e5MoAi2wiOhr0Lr1YB6yg.jpg

    https://github.com/Acly/krita-ai-diffusion

    Generate images from within Krita with minimal fuss: Select an area, push a button, and new content that matches your image will be generated. Or expand your canvas and fill new areas with generated content that blends right in. Text prompts are optional. No tweaking required!

    This plugin seeks to provide what "Generative Fill/Expand" do in Photoshop - and go beyond. Adjust strength to refine existing content (img2img) or generate images from scratch. Powerful customization is available for advanced users.

    Features

    Features are designed to fit an interactive workflow where AI generation is used as just another tool while painting. They are meant to synergize with traditional tools and the layer stack.

    • Inpaint: Use Krita's selection tools to mark an area and remove or replace existing content in the image. Simple text prompts can be used to steer generation.
    • Outpaint: Extend your canvas, select a blank area and automatically fill it with content that seamlessly blends into the existing image.
    • Generate: Create new images from scratch by decribing them with words or existing images. Supports SD1.5 and SDXL.
    • Refine: Use the strength slider to refine existing image content instead of replacing it entirely. This also works great for adding new things to an image by painting a (crude) approximation and refining at high strength!
    • Control: Guide image creation directly with sketches or line art. Use depth or normal maps from existing images or 3D scenes. Transfer character pose from snapshots. Control composition with segmentation maps.
    • Resolutions: Work efficiently at any resolution. The plugin will automatically use resolutions appropriate for the AI model, and scale them to fit your image region.
    • Upscaling: Upscale and enrich images to 4k, 8k and beyond without running out of memory.
    • Job Queue: Depending on hardware, image generation can take some time. The plugin allows you to queue and cancel jobs while working on your image.
    • History: Not every image will turn out a masterpiece. Preview results and browse previous generations and prompts at any time.
    • Strong Defaults: Versatile default style presets allow for a simple UI which covers many scenarios.
    • Customization: Create your own presets - select a Stable Diffusion checkpoint, add LoRA, tweak samplers and more.
    • Like 2
    • Thanks 1
  7. I finished the mission yesterday, i think it will remain as one of my favorites. The only thing I didn't like so much was the ending, giving the antidote to the girl, after putting the spider into orbit with the mine. Something twisted about having to first take the antidote out of the inventory to release it on the girl, instead of being able to apply it directly and a little more reaction from her, would also have been desirable.
    But hey, overall I really enjoyed this mission.

    • Like 1
    • Thanks 1
  8. I use noclip only when I get stuck, what ocurres sometimes in some missions. Godmode in missions with much scaling and manteling (I¡m not so good in this), but this don't give an big advantage in a mission, only avoid to hurt me innecesary falling from a roof.

    Notarget, to have fun in old, many times played missions, trolling guards, spawning big spiders or zombies. often with hilarious results.

  9. 9 hours ago, MirceaKitsune said:

    I quite like this idea and am in favor of seeing it in vanilla! Especially as the implementation is an easy and intuitive one that doesn't conflict: Hold the sprint key while opening or closing doors in order to slam them. I often feel I'm waiting too long for doors to open so I can get through, this would make runs more fluid granted it retroactively works on existing standard doors in all FM's.

    But there should be one caveat: Slamming a door should cause a slight alert and draw the AI's attention. I think long ago I complained about the lack of realism in AI never wondering why a door is mysteriously moving right in front of them, even if they don't see the player directly: This would be a good excuse to keep normal opening as is but have fast opening make a louder sound that draws just a bit of attention from enemies.

    Well, Ithink, talking about AIs in TDM is quite debatable, something more real AI would really be desirable. It should be possible with the number of scripts and APIs that are emerging in recent times, to be able to implement it, at least in some characters. 

    • Like 1
×
×
  • Create New...