Is anyone working on a variation of this where the output is a blender scene?
I am very interested in possibilities of generating 3d models as well. There is a fair amount of 3d models out there so it should be possible. I suspect we will end up using multiple 2d images at different angles to generate a 3d model. I have seen this done before
Try Stable Diffusion's Img2Img Mode
151–160 of 166 posts
Re: Try Stable Diffusion's Img2Img Mode
#152Try img to img using decentralized cloud: https://mirror.xyz/bitkevin.eth/F3cZoh630VvRKgmPzVQ3QXM5gQu_...
The article describes how to store a picture in “decentralized” storage.
You’re not running img2img in a “decentralized cloud”.
Re: Try Stable Diffusion's Img2Img Mode
#153Earlier quoted context omitted.
I'm running 1660 ti on Windows 11. I'm thinking about getting a 3090 so that I can make higher resolution images. Gfpgan runs much faster for me 5 seconds per picture
What resolution could you get on a 3090?
No idea, things are changing very quickly now
Re: Try Stable Diffusion's Img2Img Mode
#154Earlier quoted context omitted.
You must have missed the last 50 years with that much fear of change. Yikes.
Not sure why i deserve so much toxicity. We obviously work in different fields and have different view of what art actually is. No i am not happy to jump on AI bandwagon that will surely mean even faster pace and more precarious working conditions because individuals surely wont reap the benefits of automation. It's easy to not care when you are not affected. None of that mean that i deserve the hate. It's just a dif…
No post body was provided.
Re: Try Stable Diffusion's Img2Img Mode
#155I though it is a joke when seeing the random pixels.
Try again after seeing this post made into front page, it's actually working (and relatively very fast), just the loading screen is misleading ...
Re: Try Stable Diffusion's Img2Img Mode
#156If you upload an image with 2:1 aspect ratio it squishes it to 1:1 instead of letting you crop it. Seems like a basic thing they could add.
I bet you could add it yourself, or at least comment on it on the GitHub.
Yeah, I just didn't know if that control was part of this project or a standard part of the website.
Re: Try Stable Diffusion's Img2Img Mode
#157I keep providing drawings, and it mostly just produces other drawings. Thought it was to fill in content accordingly. What am I missing?
Re: Try Stable Diffusion's Img2Img Mode
#158I've been trying to get some sensible images out of my descriptions, but I fail miserably. In this case I had the prompt "cow chewing bone" with 4 squares representing the two pair of feet, the body and the head. None cared about chewing on a bone. With DALL·E 2 I tried to get an image of a little girl building sandcastles and a monster threatening her: "little scared girl building a sandcastle and a big angry monste…
Yes, checkout examples on lexica or use a prompt builder to help, like promptmania. Also, most of the good ones you see online are cherry picked from hundreds of runs, so set your batch size too 1000 and go to bed! After that, people then tend to run some of the good results through img2img, also with a lot of variations produced from a single image. Finally, some people also run them at higher resolutions if they ha…
Just know that if you let it run over night often, you will see it on your electricity bill. My GTX 1660 runs at max while rendering, which is 125W. Leaving it running over night can easily eat 2 to 6 kw's, depending on your system.
Re: Try Stable Diffusion's Img2Img Mode
#159If you have a GPU with >4GB of VRAM and you want to run this locally, here's a fork of the Stable Diffusion repo with a convenient web UI: https://github.com/hlky/stable-diffusion It supports both txt2img and img2img. (Not affiliated.) Edit: Incidentally, I tried running it on a CPU. It is possible, but it took 3 minutes instead of 10 seconds to produce an image. It also required me to hack up the script in a really…
Can you share your script for running on CPU?
python optimizedSD/optimized_txt2img.py --device cpu --precision full --prompt "…" --H 512 --W 512 --n_iter 1 --n_samples 1 --ddim_steps 50
Re: Try Stable Diffusion's Img2Img Mode
#160Earlier quoted context omitted.
Can you share your script for running on CPU?
python optimizedSD/optimized_txt2img.py --device cpu --precision full --prompt "…" --H 512 --W 512 --n_iter 1 --n_samples 1 --ddim_steps 50
Thank you. There was a also a related submission for running on CPU: https://news.ycombinator.com/item?id=32642255
I'm planning to try it out this weekend. But not really hopeful. I only have 8GB ram, and mine is a cheap Intel CPU that doesn't even have AVX.