CreatixAi - content about Ai (Artificial Intelligence) Technology - Ai Art, Text, Video and Music. Join me on this journey of combining creative vision and intelligent ingenuity. Thank you for watching!
You start with the prerequisites.. but miss the most important. You need a card with 24gigs of VRAM With no second hand 3090s on the market any more, that means pumping down almost 2 grand on a 4090. If I would have known that up front I could have saved myself 11 minutes.
The tutorial is very clear, but unfortunately the program UI is now completely different and I failed to successfully reproduce anything. When going to train it gives " No data found. Please verify arguments (train_data_dir must be the parent of folders with images)" even through I reproduced literally everything you did, including folder naming.
Hi, this is great, I learned so much from that video. The video was a little bit of to the audo though, I sometimes got lost in what you were saying and what was happening. The output I received is insane though. Thank you so much, You did an amazing job in this video. I'd like to see more of Your content!
I followed the tutorial as you indicate and when I click on generate it gives me this error: AttributeError: 'NoneType' object has no attribute 'shape' I don't know if you have any solution?
Great guide. Got it right on my first go without using Kohya before. My only question is why did I only get three LORAs even though I asked for ten epochs and had "Save every N epochs" set to 1?
After installation, when I start it from pinokio, returns an error that says: ENOENT: no such file or directory, stat 'C:\pinokio\api\triposr.git\{{input.event[0]}}' Any idea about how to fix it?
I get the same thing. Terminal says: Traceback (most recent call last): File "C:\pinokio\api\triposr.git\app\app.py", line 6, in <module> import gradio as gr ModuleNotFoundError: No module named 'gradio'
Hello, thank you for your good training🙏🙏 I have a question: After installing pinokio, I encountered a JavaScript error when running the program👇🏻👇🏻 Error listen EACCES: permission denied 0.0.0.0:80 Can you guide me how to fix this problem and error?
somehow my results are unsatisfying with stable diffusion automatic 1111 when trying to generate locally on my pc with my old gpu gtx 1080 ti 11gb, cant even get anything close to just even looking good or anything comparable, if i have to be honest automatic 1111 local generation cant even compare to the simple and basic generation of leonardo ai
You'll still need to decimate the models before importing them into a game engine as the polycount is not worth it as is. Too expensive perf wise and most results would still take hours to prepare and cleanup to be useful. Waste of time IMO, especially if it's for a second in a cutescene. Also a waste of player's disk space. Just use a 2d plane with a low res texture made from the original prompt. That would be way better. Taking the milk bottles as an example prop, Just make a cube and properly UV map the 2d prompt as a texture. Faster and cheaper (computing and storage wise). Anyway, it could still be useful as a base for sculpting in Blender or doing a retopology on top and, in that regard, i wish it was a blender plugin with a prompt to 3d pipeline.
I got a new laptop (4090). I noticed when I start training my gpu in task manager performance tab stays at 0%? Training is still proceeding but why is that? Brand new laptop. Yours shows this for comparison 16:24
nice to meet you. Thank you for the wonderful explanatory video. Even if the conditions are the same depending on the character, things may not go as well as you did. I think one possible point is that the prompts are different. Could you please share if possible?
Nice videos. But it all looks meaning less, if you can't make a full length movie with continued story and characters. Even with seeds and prompts. Hopefully, that day will come soon. 🌷🌷🙏♥️👄
although your voice is cute and tutorial is awesome but you teach us very stupiddd rude mad difficult way very new person needs more easy teaching way plz can you plz make same tutorial in FOOOCUS plzzz
Very interesting. Thank you for covering it so good and so quickly. I specially liked when you demoed them in blender and Maximo. Very cool. I wish the faces looked better. Definitely post one that has better 3D faces anytime you find it. Processing time is not a big issue, if the result is reliable. Thank you again
No they won't. 3D is not the same as images, it's far more complicated. It will probably be before the end of the decade but AI isn't going to be popping out high quality 3D models from images in the next couple of years. It's also unlikely to develop to a high level using a mesh workflow anyway, it's more likely going to eventually advance using techniques similar to Gaussian Splatting and AI driven point cloud systems. A lot people interested in generative AI always have this idea that everything is going to be solved by the end of the year :D
Quick question. If I have an existing photo with an existing segmentation, depth and even normal map. Is there a way use them all as inputs (instead of estimations) and using them all simultaneously in the calculation rather than using them seperately (depth only, mask only etc)