SDXL Turbo: A Real-Time Text-to-Image Generation Model
1–10 of 157 posts
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#2The license is non-commercial, but:
> For clarity, Derivative Works do not include the output of any Model.
https://huggingface.co/stabilityai/sdxl-turbo/blob/main/LICE...
Doesn't that mean that generated images from it should be fine for commercial?
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#3Awesome! so where is the API I can try?
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#4Awesome! so where is the API I can try?
They have a web demo here: https://clipdrop.co/stable-diffusion-turbo
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#5Awesome! so where is the API I can try?
They have a web demo here: https://clipdrop.co/stable-diffusion-turbo
...which requires you to sign in. That nice little text box invites you until you actually click to enter some text and get a registration box thrust at you
People that design a UX where the user tricked into a registration 'ambush' need to be punched in the face.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#6Earlier quoted context omitted.
They have a web demo here: https://clipdrop.co/stable-diffusion-turbo
...which requires you to sign in. That nice little text box invites you until you actually click to enter some text and get a registration box thrust at you People that design a UX where the user tricked into a registration 'ambush' need to be punched in the face.
Luckily this one accepts burner emails just fine, without any intrusive other data collection (name, etc)
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#7Based on the demo, that's... incredibly fast. Literally generating images faster than I can type a prompt. They've clearly got a set seed, so they're probably caching request, but even with prompts that they couldn't possibly have cached it's within a second or so.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#8I've been mucking with this stuff again and the SDXL + LCM sampling & LoRA makes 1280x800 images in like 2 second, so about a ~5x speed increase for me (so this would be roughly 2x faster than LCM (??, napkin math)). I've found that the method isn't as good at complex prompts. They claim here this can outperform SDXL 1.0 WRT prompt alignment, but I'm curious what their test methodology is. I searched the paper and I couldn't immediately find how it was evaluated. I think these sorts of subjective measurements are fiendishly hard to quantify given the infinity of possible prompts. Still, exciting stuff always happening here, what a time to be alive.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#9I've been mucking with this stuff again and the SDXL + LCM sampling & LoRA makes 1280x800 images in like 2 second, so about a ~5x speed increase for me (so this would be roughly 2x faster than LCM (??, napkin math)). I've found that the method isn't as good at complex prompts. They claim here this can outperform SDXL 1.0 WRT prompt alignment, but I'm curious what their test methodology is. I searched the paper and I…
the use case here is really for segmented inpainting.
don't like a part of an image? replace it instantly
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#10I've been mucking with this stuff again and the SDXL + LCM sampling & LoRA makes 1280x800 images in like 2 second, so about a ~5x speed increase for me (so this would be roughly 2x faster than LCM (??, napkin math)). I've found that the method isn't as good at complex prompts. They claim here this can outperform SDXL 1.0 WRT prompt alignment, but I'm curious what their test methodology is. I searched the paper and I…
the use case here is really for segmented inpainting. don't like a part of an image? replace it instantly
There are SO many use cases! I maintain we're not even scratching the surface here. You could programmatically reskin video based on crowd participation, you could re-texture VR spaces on the fly. The space of cool shit that you can do with this stuff is growing far faster than we're able to explore it right now.