The more AI-generated art I see the more convinced I am that it will generate entire new modes of art creation, rather than make creative work redundant.
I'm now waiting for a creation that could not have been done without AI, the labour that would be involved to create these works manually not being considered.
Very cool! I just released a tutorial on how to do this using the computerender api!
https://github.com/computerender/tutorials/tree/main/python/...
If you’re interested in saving money on expensive cloud gpus, our api is much cheaper than this. (only $0.001-0.0025 per frame)
I suggest that people simply run Stable Diffusion Deforum themselves (there's an extension for automatic1111's web UI). You can run it in a google colab notebook and the cost will likely be cheaper or the same, though I haven't bothered to compare.
Reminds me a lot of the "Ghost" music video for by Gunship[1] made by aiplague[2].
Reminds me of something you would see in a newer modern remake of Decasia.
https://en.wikipedia.org/wiki/Decasia https://www.youtube.com/watch?v=hDa-mmSldDg
Very cool, your demo video looks great, would love to try it when it's working again. You can also do this type of thing on colab with Deforum Stable Diffusion: https://colab.research.google.com/github/deforum-art/deforum...
I've been messing with it myself, here is an example: https://youtu.be/FsVskNtNazk
Couple suggestions after playing with this:
1) the experience mostly works on mobile (where I first tried it). With only minimal changes in the fixed sizing I think you could make this mobile friendly.
2) for posts shared via your Twitter, would be interesting to see details about the prompt(s) used vs “new post”
3) I’d like to have a bit more customization in the options
Overall really nice and good luck with monetizing it. I’d love to see a blog post write up on the technical implementation. That’s something I’d more be willing to pay to see personally.
Yannic kilcher had created a videoclip for lyrics made of imagenet labels last year: https://www.youtube.com/watch?v=rR5_emVeyBk
This is very cool! What sort of values are you using for the denoising strength/guidance scale? Each frame is a nice level of similar/different to the last to create flowing video.
Nice! This is much simpler than using Deforum
Is everything set up on the cloud yourself, or do you use an API?
Is there an example video somewhere?
Edit: Nevermind - I don't have autoplay active and there was no way to see that the "image" on the landing page is actually a video (no UI like a play button).
What prompts did you use to make the video?
The description of what you have to do reminds me the instructions on how to draw an owl (https://knowyourmeme.com/photos/572078-how-to-draw-an-owl)
The site should have a demo video of what an output looks like instead of a static image.
I stopped at the signup form.
Might want to put notice:
“There's a lot of requests currently and our servers are overloaded - sorry. I am trying to increase the capacity. Please try again later.”
…prior to making users do multiple clicks, opt to not provide an email, etc.
Even a prerecorded demo posted to Youtube would be a better experience.
Might want to put notice:
“There's a lot of requests currently and our servers are overloaded - sorry. I am trying to increase the capacity. Please try again later.”
…prior to making users do multiple clicks, opt to not provide an email, etc.
...no noise overlay on the input images to at least get some sort of frame by frame consistency? -.-
The company that makes stablediffusion is being sued for copyright infringement. Don't use this.
Hi all, thanks for all that attention to the site. I am super happy about that. A word of caution: I can only rent 4 GPU instances currently on AWS due to service quota limits. "Unfortunately" the traffic due to hackernews is too high for that. Sorry for any inconveniences. If you are having troubles at the moment, come back later or so. I asked for service quote increase but those take usually 24h or so.
Also, very little people actually pay so I can only afford so much.