What are the most affordable GPUs that will run this? (it said it needs CUDA, min 11GB VRAM, so I guess my relatively puny 4GB 570RX isn't going to cut it!)
Whatever 3060 variant that has the most VRAM is probably your best shot these days.
Show HN: New AI edits images based on text instructions
121–130 of 241 posts
Re: Show HN: New AI edits images based on text instructions
#122What are the most affordable GPUs that will run this? (it said it needs CUDA, min 11GB VRAM, so I guess my relatively puny 4GB 570RX isn't going to cut it!)
It works fine on CPUs. Takes about a minute to generate images on my 8 core i7 desktop.
How do I get it to use CPU rather than GPU, please? I have 128GB of RAM but a lowly 2GB of VRAM in my PC.
Re: Show HN: New AI edits images based on text instructions
#123If only Stable Diffusion wasn't already populated with a host of copyrighted images already.
Make your own art, dammit. This is the equivalent running some Photoshop filters through someone else's work.
Re: Show HN: New AI edits images based on text instructions
#124Earlier quoted context omitted.
Huh, I'm trying it now and the results seem so weak compared to any other model I've seen since dall-e.
Hmm that’s true for me too. Not sure if it is due to resource constraint. I had a picture of a car in indoor parking lot with walls and pillars. When I prompted “Color the car blue” the whole image was drenched in a tint of blue. Similarly when prompted “make a hummingbird hover” … the hummingbirds were a patch of shiny colors with an shape that sort of looked like an hummingbird but not like a real one.
Try "turn the car blue"
Re: Show HN: New AI edits images based on text instructions
#125Earlier quoted context omitted.
It works fine on CPUs. Takes about a minute to generate images on my 8 core i7 desktop.
How do I get it to use CPU rather than GPU, please? I have 128GB of RAM but a lowly 2GB of VRAM in my PC.
Try setting the CUDA_VISIBLE_DEVICES environment variable to ''.
Re: Show HN: New AI edits images based on text instructions
#126Earlier quoted context omitted.
The cheapest NVidia GPU with 11+GB VRAM is probably the 2060 12GB, although the 3060 12GB would be a better choice. The setup.py file seems to indicate that PyTorch is used, which I think can also run on AMD GPUs, provided you are on Linux.
I really want these ML libraries to get smarter with use of VRAM. Just cos I don't have enough VRAM shouldn't stop me computing the answer. It should just transfer in the necessary data from system ram as needed. Sure, it'll be slower, but I'd prefer to wait 1 minute for my answer rather than getting an error. And if I don't have enough system RAM, bring it in from a file on disk. Tha majority of the ram is consumed…
Using RAM to hold unneeded layers was one of the first optimizations made for Stable Diffusion. The AUTOMATIC1111 WebUI implements it, not sure about others.
Re: Show HN: New AI edits images based on text instructions
#127Slightly off topic.
I’ve been looking for an easier way to replace the text in these ai generated images. I found Facebook is working on it with their TextStyleBrush - https://ai.facebook.com/blog/ai-can-now-emulate-text-style-i... but have been unable to find something released or usable yet. Anyone aware of other efforts?
Re: Show HN: New AI edits images based on text instructions
#128How about “fix the hands”?
The hands issue is going to be an awesome story for all of us in 10-20 years. The younger generation just won’t fathom how hard it was to get proper hands. I wonder what a parallel comparable now would be? Something the slightly technical general public just can’t wrap their head around why it was complicated “back then”.
Maybe todays example is a smart voice assistant like Alexa.
Re: Show HN: New AI edits images based on text instructions
#129These look awful! They are very displeasing aesthetically. They look like they were done by someone with absolutely no artistic ability. Clearly there is some technical interest here, but I just felt the need to point out the elephant in the room. They are very ugly.
Re: Show HN: New AI edits images based on text instructions
#130Earlier quoted context omitted.
I'm running on a 2080 TI and an edit runs in 2 seconds. On my Apple M1 Max 32Gb edits take about 60 seconds.
If this was all packaged into a desktop app (e.g. Tauri or electron) how big would the app be? I'd imagine you could get it down to < 500MB (even if you packaged miniconda with it).
> I'd imagine you could get it down to I don't know where that imagined number came from. This tool appears to be using Stable Diffusion, and the base Stable Diffusion model is 4 or 5 gigabytes by itself. I think there are some other models that are necessary to use the base Stable Diffusion model, and while they are smaller, they still add to the total size.