Recent Posts

1

Gallery / Japandi Milano Kitchen Interior

« Last post by Pikcells on Today at 16:39:22 »

In this kitchen interior our 3D artists have meticulously crafted a modern kitchen setting infused with Japandi charm. For those not yet acquainted with the interior design trend, Japandi seamlessly blends the clean lines and functionality of Scandinavian design with the minimalist elegance and Zen-inspired serenity of Japanese style. Every element, from the sleek lines of the cabinetry to the curated selection of props faithfully in 3D recereated for the shelving areas have been included to reflect the essence of the Japandi design movement. Our artists also concentrated additional time ensuring that the textures and finishes, particularly in the ribbed oak panels and doors (another current interior design trend), are of the highest quality. The rich textures add depth and character to the design, contrasting against the matt black cabinetry and further elevating the appeal of the space.

More about this kitchen > https://www.pikcells.com/blog/ideal-home-kitchen-awards-2024

2

Work in Progress/Tests / Re: Juraj's Renderings thread

« Last post by TomG on Today at 14:42:09 »

My apologies too, to Juraj :O

I started with ComfyUI, and picked it as I like node based editing vs. how Automatic1111 works; also there were "just download and run this and everything installs" for ComfyUI vs. "Go to github, download this, run some weird command, now go back to github to download this other thing, also be sure to install Python..." which I did not want to mess with ;) Plus then the Manager you can install into ComfyUI that makes it easy to install loads of other things, including automatically finding and installing missing nodes or functions used in a workflow (the "drag and drop the PNG output from ComfyUI into ComfyUI and it recreates all the nodes and prompts right there" is something else I also really like - no need to save that separately, it is all embedded in the image, and of course this makes it easy to get someone else's ComfyUI set up, just drop their image in there when they provide it for that purpose).

3

Work in Progress/Tests / Re: Juraj's Renderings thread

« Last post by romullus on Today at 14:30:36 »

(sorry to hijack the thread a bit here feel free to move into a new thread)

I think it would be better indeed if someone would start a new all things AI related topic, as such questions will only increase in the near future.

And at the risk of completely derailing Juraj's thread, may i ask you Tom, why did you choose ComfyUI instead of more "traditional" UI? For the past few weeks i'm completely immersed in this new for me topic. Lately i'm thinking about switching to ComfyUI, since it looks that's where all the power and flexibility is, but i'm afraid that it might be overwhelming experience with node system when i don't know basics well enough yet. Did you choose Comfy since the beginning, or did you switch to it from some other UI?

4

[Max] Daily Builds / Re: CoronaPattern playground!

« Last post by alexyork on Today at 14:15:35 »

Hi devs,

I've lost track a bit of previous requests/emails etc. but I'm compiling a short list below of my wish-list changes for PatternMod - could you please update us on progress in these (and other) areas?

And just to front-load the conversation, I know that the usual response (fairly!) is "why don't you just use ChaosScatter for this?" but there's something very simple and very nice about the speed, elegance and simplicity of PatternMod that makes me keep coming back to it, especially for carpet/rug stuff. I'm getting some very good results out of it but with a few improved features it could be really killer:

- Can we please get randomisation controls for Pattern Height?

- Can we please get map-driven everything? Especially Pattern height / offsets / rotations, and ideally the surface itself (beyond limiting to matID as currently). It would be awesome to load in for example a greyscale map that would determine where the pattern appears, and another one that determines how high it appears.

- Will it be possible one day to have the source object not be trimmed/clipped? In this way, if you do for example 0.5 shifting you will still see the entirety of the source object, allowing you to get a much more randomised and natural "scattering" effect (when this is desired - for example when making carpets/rugs).

- Can you update us on if it will ever be possible to enable PatternMod to be used on top of an object already using rendertime displacement?

- Can you please consider making it possible to multiple-stack CoronaPatternMod modifiers on a single object? This would be helpful for certain complex randomisations etc. (until we can get real randomisation/offsetting controls).

5

[Max] Bug Reporting / Re: CoronaMultiMap seed changes with animated camera

« Last post by dzintas on Today at 13:59:43 »

Hi,

I have checked the scene and unfortunately this is expected given how the VRay proxy is animated.
The number of faces (and effectively their indices) changes, and so does the randomization.

I think the workaround is to have different IDs for the roofs and randomize by Material ID instead of Mesh Element.

Hope this helps.

I'll try it out if encounter this bug again. At the moment just smoothed over the flicker in post and work on it is finished for now. Unless we get some revisions.
About the process, for example my roof material. I need to create multiple material id's for same roof material just to have some randomization to happen?
Kind of complicates the process a bit.
Other thing, would this happen if I use point cache or corona proxy instead of vray proxy?

 

6

Work in Progress/Tests / Re: Juraj's Renderings thread

« Last post by TomG on Today at 12:32:56 »

In the workflow I tested, I was using upscaling inside ComfyUI (so, Stable Diffusion run locally). I did indeed crop the whole person (and some surrounding area as it was a crude rectangle mask, which I would mask out when overlaying into the image, so I drew the more detailed mask at the end as it happens :) ), as I wanted to improve the skin and clothing overall as well as the all-important face. Hope this helps!

7

Work in Progress/Tests / Re: Juraj's Renderings thread

« Last post by dj_buckley on Today at 12:15:39 »

I will leave Juraj to comment on his workflow :) I have tested something similar this last week though, using ComfyUI, and I can say that trying to do "face improvement" at 512x512 does not work, it just uglifies things :) For me I had to take a crop of my test image which ended up being 374 x 669, upscale it through a 4x upscaler to 1496x2672, then pass that through the Realistic model with 0.49 denoising, and then it improved clothes and faces. Trying to do that on the original crop with no upscaling just made things worse - so in the way I had things set up, a) you are not limited to 512 at all and b) 512 makes things worse.

This may be dependent on GPU memory though.

For interest, this was on a 4080 laptop GPU with 12GB memory, with similar performance seen on a 3070 Ti desktop. It was about 60 seconds to process the crop (that is to upscale it with a face sensitive upscaler, and then feed it through the model, combined in that time)

Also Tom (sorry to hijack the thread a bit here feel free to move into a new thread), i'm assuming here that your crop was of the whole person, so in effect the face was much much smaller than 374 x 669 crop.  The upscale then allowed the 'face' to fill the 512 marquee better in the resulting 1496x2672 image giving more starting fidelity for SD to work with?

8

Hardware / Re: Threadripper issues

« Last post by gmh_2001 on Today at 11:06:36 »

@maru Do you have 3990x and 3970x machine on latest build Win 11 and latest bios/chipset drivers etc..to test these files?

9

Hardware / Re: Threadripper issues

« Last post by gmh_2001 on Today at 11:03:59 »

I can't share the files due to NDA. So I will have to create a test file to upload..

10

Work in Progress/Tests / Re: Juraj's Renderings thread

« Last post by dj_buckley on Today at 10:38:27 »

upscale it through a 4x upscaler to 1496x2672

Hey Tom, are you referring to an  external upscaler like Topaz here or an AI upscaler inside Stable Diffusion, just wrapping my head around all this stuff