Software Engineering Courses (SECourses)•15mo ago

hey guys, does anyone know of a tool that can generate 3d models from a single image? I think i reme

hey guys, does anyone know of a tool that can generate 3d models from a single image? I think i remember seeing something like this somewhere but cant video the video.

Vinch•10/4/24, 5:53 PM

I've never tried pro. Would one say that pro is significantly better than dev?

VVinch I've never tried pro. Would one say that pro is significantly better than dev?

crystalwizard•10/4/24, 6:02 PM

it's better, not significantly however. and it's EXPENSIVE to run the api

Xxlads hey guys, does anyone know of a tool that can generate 3d models from a single i...

Dazzastrous [4090]•10/4/24, 6:07 PM

Meshy

crystalwizard•10/4/24, 6:09 PM

the new model for meshy is really good, too

Dazzastrous [4090]•10/4/24, 6:10 PM

yeh can animate

crystalwizard•10/4/24, 6:10 PM

yes, but it's also very good just creating the mesh and the images from it.

Dazzastrous [4090]•10/4/24, 6:10 PM

yeh one of the best

crystalwizard•10/4/24, 6:11 PM

what you want, really, is to be able to download the mesh and use it in a video game or in blender, and it seems to ahve that well in hand. just need it to rig now

PixelMonkey•10/4/24, 6:24 PM

to follow up on that weird line issue.. i dont think its overfit.. i have the feeling it has to do with the image res and aspect ratio? when i reduce my image size to generate with 720x 960 instead of 896x1152 i dont get the weird artefacts... but the quality of the images decreases quite a bit. what do you guys use for image aspects ratios and how do you prevent/fix this ?

PixelMonkey•10/4/24, 6:25 PM

So basically anything below 1024x1024 makes it better i feel

PPixelMonkey So basically anything below 1024x1024 makes it better i feel

crystalwizard•10/4/24, 6:50 PM

that's pretty standard. it has everythign to do with whether the AI was trained on images that were all the same AR or if it was trained on images of all different ARs. if they were all the same AR - then it knows how to draw that and things get wierd when it tries to draw some other aspevt ratio

crystalwizard•10/4/24, 6:52 PM

you see that a lot with stable diffusion 1.5 - which was trained on 512x512 images. ask for an AR that's not 512x512, what it does is draw multiple 1:1 AR images and concatenate them together - resulting in heads on top of heads in a 9:16 image or other strangeness

EEyeSpyBekoAI Flux 1.1 is out and that could only mean one thing. @Dr. Furkan Gözükara , have ...

Furkan Gözükara SECourses•10/4/24, 6:55 PM

i hope its dev version get released

EEreshkigal Question for you guys, as I'm having issues finding an answer thus far: Has anyo...

Furkan Gözükara SECourses•10/4/24, 6:55 PM

you can mix

Furkan Gözükara SECourses•10/4/24, 6:55 PM

at worst case you can reduce timing

AAryan Guys did anyone try flux 1.1

Furkan Gözükara SECourses•10/4/24, 6:56 PM

i found that it is nice for prompts like a dinasasur

BB0nd anyone else having issues with runpod today?

Furkan Gözükara SECourses•10/4/24, 6:56 PM

what issue you have

Furkan Gözükara SECourses•10/4/24, 7:08 PM

I have dumped T5 XXL token list and working on a new rare token

Furkan Gözükara SECourses•10/4/24, 7:08 PM

that will be rare in T5 too

Falan•10/4/24, 7:19 PM

@Dr. Furkan Gözükara , I trained my own LoRA Flux with the Flux FP8 model, and I want to generate images with my LoRA for free on Kaggle. Before I subscribe to your Patreon, I wanted to ask if your Patreon post about "Free Kaggle Account Notebook for SwarmUI with Stable Diffusion 3 and Dual T4 GPU support" , can use FP8 LoRAs ?. I previously tried using Forge , but the images result were blurry and pixelated.

FFalan @Dr. Furkan Gözükara , I trained my own LoRA Flux with the Flux FP8 model, and I...

Furkan Gözükara SECourses•10/4/24, 7:21 PM

yes it can use

Furkan Gözükara SECourses•10/4/24, 7:21 PM

but cant train

Furkan Gözükara SECourses•10/4/24, 7:22 PM

blurry result happens due to cfg not being 1

Furkan Gözükara SECourses•10/4/24, 7:22 PM

we use latest swarmui and comfyui as backend

Furkan Gözükara SECourses•10/4/24, 7:22 PM

works perfect

PPixelMonkey So basically anything below 1024x1024 makes it better i feel

NeonNinjaAstro•10/4/24, 8:34 PM

been getting good results sometimes by using Flux at 512*512512*512 or even 384*384384*384 in the first pass

NeonNinjaAstro•10/4/24, 8:35 PM

the VAE is so much better than SDXL so you can do more passes

NNeonNinjaAstro been getting good results sometimes by using Flux at ``512*512`` or even ``384*3...

PixelMonkey•10/4/24, 8:42 PM

How do you do mutliple passes? Are you running it in Comfy Ui? I am still on Web Ui Forge

NeonNinjaAstro•10/4/24, 8:43 PM

yeah in Comfy, but you can do this in Forge as well

NeonNinjaAstro•10/4/24, 8:44 PM

what you need to do is take the result of the first pass

NeonNinjaAstro•10/4/24, 8:44 PM

upscale it using an external upscaler

NeonNinjaAstro•10/4/24, 8:44 PM

and then do the standard img-to-img in Forge using a denoise % less than 1

IWishIWereGood•10/4/24, 9:17 PM

Hi everyone, should I use regularisation images when training a lora on sdxl?

IIWishIWereGood Hi everyone, should I use regularisation images when training a lora on sdxl?

Furkan Gözükara SECourses•10/4/24, 9:17 PM

1024x1024

Furkan Gözükara SECourses•10/4/24, 9:18 PM

testing flux rare tokens

Furkan Gözükara SECourses•10/4/24, 9:19 PM

single words makes such good images

Furkan Gözükara SECourses•10/4/24, 9:19 PM

DDazzastrous [4090]Meshy

xladsOP•10/4/24, 9:21 PM

Came out really low quality with the details on my face, maybe I’ll try with another image

Ccrystalwizard what you want, really, is to be able to download the mesh and use it in a video ...

xladsOP•10/4/24, 9:21 PM

Yep!

xladsOP•10/4/24, 9:24 PM

It would be so cool if we could generate videos with our models using text to video. Is there anything out like this? @Dr. Furkan Gözükara

Xxlads It would be so cool if we could generate videos with our models using text to vi...

crystalwizard•10/4/24, 9:28 PM

there are lots of text to video AIs out there - and meta just annouced this https://ai.meta.com/research/movie-gen/

AI at Meta

Meta Movie Gen - the most advanced media foundation AI models

Meta Movie Gen is our latest research breakthrough that allows you to use simple text inputs to create videos and sounds, edit existing videos or transform your personal image into a unique video.

Xxlads It would be so cool if we could generate videos with our models using text to vi...

Furkan Gözükara SECourses•10/4/24, 11:18 PM

nothing good

Ccrystalwizard there are lots of text to video AIs out there - and meta just annouced this http...

Furkan Gözükara SECourses•10/4/24, 11:18 PM

i am about to publish a video for it

Ccrystalwizard there are lots of text to video AIs out there - and meta just annouced this http...

xladsOP•10/4/24, 11:21 PM

Yes, I heard about this, but we’re unable to use our own trained models