I like the idea of node based image editing. It reminds me of when learning how to write shader code for games and GLSL was waaaay too over my head until I discovered node based shaders, and I didn't have to wrangle with coding and instead focusing experimenting with different nodes.
However soon creating a "shader that works" was no longer an issue but how to create X effect using shaders was my next blocker, and luckily there were ton of YouTube tutorials on these, which was very helpful, but this continues to be a pain point even now
Since now we are in the age of AI, would it be possible to prompt something like "create me a workflow to take image A, a concept art of a character and convert into into a walking animation sprite sheet with 16 frames for each animation walking up, down, left, right and all diagonal directions" and have it not only generate the result, but a workflow to create the result so it can be edited and tweaked.
Oh yea I know what you mean. There are several parallels here with shader nodes for sure. We've been thinking about a voyager/agent-style approach where an agent can start to learn "skills" where skills are individual blocks. Each skill represents a certain function applied to an image and based on a specific instruction set we should be able to craft a sequence of actions that will lead to that result.
One way to leverage that is building the graphs via a prompt, but another way might be to not think of the workflow as a pre-constructed graph at all. Rather perhaps we build dynamic graphs whenever you ask for a certain action - like a conversational image editing interface.
So you say something like make the woman's hair purple. We apply segmentation to the hair, and then add a puple color overlay exactly to that area.
I prototyped a system one year ago which created node-based, editable scene graphs in-browser with the help of an LLM-powered agent. It allowed the user to quickly construct complex 3D scenes.
It was some amazing tech with a ton of applications, but sadly leadership had other plans and pivoted to a highly derivative, slapped-together AI sex bot.
The walking animation is going to be a lost cause without specific inputs. We can do ControlNet stuff to make a character match a pose, and you can supply a series of poses that represent the walking animation.
On some level it seems silly to try and get anything to generate the workflow to do that. What you really want is a workflow to generate an image off of a pose, and then pass in the poses you want. Side tangent, I don’t know why the ai generation community has decided “workflow” is what they’re going to call “functions”?
After that your problem is that the results will be kind of meh. And that’s the brunt of where it’s at right now. You can make assets that satisfy descriptive conditions. But you can’t demand they be good. And you can’t demand they be consistent across different drawings. Can you hire an artist to fix your generated directionally correct assets? Yeah, maybe. Sounds depressing and error prone though.
Not really an apples-to-apples comparison. ComfyUI is for diffusion-focused workflows, this is not.
Plus you don't need a local GPU for this.
I realize this is a Pro for some Con for others, so there can be different products in the market serving different needs.
It's an interesting idea but I don't recommend it with current headset. I work on a VR startup but truthfully speaking the technology isn't ready for everyday use yet.
The current generation of the headset isn't ready for long term use yet, maybe when the next generation of headset come out. Reading text on the current headsets (Oculus/HTC) can give you some serious headaches and eye strain. I'd wait until next generation come out before trying.
Though one thing that VR is really good for is A/B testing designs and visualizing data.
that sounds like me a lot :)
It doesn't sound like ADHD but rather a common procrastination habit (my apologize if you are actually medically diagnosed though).
I have problem focusing on things that I'm not interested in as well, but I've learnt to accept that and not feel too guilty about it. Especially since sometime procrastination has some pretty nifty benefits: https://www.ted.com/talks/adam_grant_the_surprising_habits_o...
What I've found really helpful for things I need to get done but have trouble doing is to make a to do list (highly recommend the Todoist app). And put in things to do in the list for each day. For example, do assignment A for 20 minutes, do assignment B for 20 minutes, exercise for 30 minutes etc. Make sure you make it simple enough such that it feels achievable (don't put things like finish an entire assignment as a task unless you know it's a short one). This helps me put myself in short burst focus mode and actual be productive instead of trying to be productive and totally failing at it. Not everyone can handle the 12 hour work day and I don't think you should force yourself to. I myself can only work for 3 hours most before getting exhausted (with plenty of rest in between), but I can do these 3 hours at hyper-focus mode and get more done than what other people can do in 8 hours.
The core things to do are:
- accept the fact that not everything interest you and you'll be able to do it with focus. There's a myth in society that the longer you work the harder you work. Totally not true.
- don't overwhelm yourself with tons of tasks, the key is to make it seem like it's really easy to do to get things done. The more overwhelmed you feel the less motivated you are to get started.
- take a walk if you are getting depressed or overwhelmed, it helps A LOT!
- And don't be afraid to try different things! Maybe you are just stuck in a bad career :)
The translations are from Google Translate, but edited by hand. If there's an error, please tell me and I'll fix it! There's also a dictionary editor built in; click the Edit button and see the popup. You can upload your changes to the server, too.
However soon creating a "shader that works" was no longer an issue but how to create X effect using shaders was my next blocker, and luckily there were ton of YouTube tutorials on these, which was very helpful, but this continues to be a pain point even now
Since now we are in the age of AI, would it be possible to prompt something like "create me a workflow to take image A, a concept art of a character and convert into into a walking animation sprite sheet with 16 frames for each animation walking up, down, left, right and all diagonal directions" and have it not only generate the result, but a workflow to create the result so it can be edited and tweaked.