I'm gonna wait until this is released as a model. This is really cool though!
SDXL Turbo: A Real-Time Text-to-Image Generation Model
11–20 of 157 posts
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#12the clipdrop demo doesn't inspire much confidence with how bad the generations are, we're talking 2021 levels, not to mention everything is NSFW somehow, should probably work on those filters.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#13Hugging Face released a Colab Notebook for generation from SDXL Turbo using the diffusers library: https://colab.research.google.com/drive/1yRC3Z2bWQOeM4z0FeJ0...
Playing around with the generation params a bit, Colab's T4 GPU can batch-generate up to 6 images at a time at roughly the same speed as one.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#14I'm gonna wait until this is released as a model. This is really cool though!
From TFA:
> Download the model weights and code on Hugging Face[0], currently being released under a non-commercial research license that permits personal, non-commercial use.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#15the clipdrop demo doesn't inspire much confidence with how bad the generations are, we're talking 2021 levels, not to mention everything is NSFW somehow, should probably work on those filters.
I tested a bit and the quality for photorealistic images is surprisingly bad, and definitely worse than LCM and of course normal SDXL. For more artistic images, SDXL Turbo fares better.
Unlike normal SDXL, you're required here to use the old-fashioned syntatic sugar like "8k hd" and "hyperrealistic" to align things.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#16the clipdrop demo doesn't inspire much confidence with how bad the generations are, we're talking 2021 levels, not to mention everything is NSFW somehow, should probably work on those filters.
Yeah, it looks like the enshittification of StabilityAI is in full force by now. Especially considering the continually worse licensing.
I expect if they ever manage to release an image gen model that's an objective improvement, lets say 80% as good as dalle3, it will be subscription API only.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#17the clipdrop demo doesn't inspire much confidence with how bad the generations are, we're talking 2021 levels, not to mention everything is NSFW somehow, should probably work on those filters.
I tested a bit and the quality for photorealistic images is surprisingly bad, and definitely worse than LCM and of course normal SDXL. For more artistic images, SDXL Turbo fares better. Unlike normal SDXL, you're required here to use the old-fashioned syntatic sugar like "8k hd" and "hyperrealistic" to align things.
Are there any good resources for learning a lot of "syntactic sugar" terms? This is new to me, but I'd love to know more.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#18The 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?
I'm not a lawyer, but I believe there was a court ruling that says AI generated works cannot be copyrighted. So you could use them, but couldn't stop anyone else from doing what they want with them
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#19Earlier 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.
A totally reasonable response to a minor inconvenience.
Re: SDXL Turbo: A Real-Time Text-to-Image Generation Model
#20the clipdrop demo doesn't inspire much confidence with how bad the generations are, we're talking 2021 levels, not to mention everything is NSFW somehow, should probably work on those filters.
Yeah, it looks like the enshittification of StabilityAI is in full force by now. Especially considering the continually worse licensing. I expect if they ever manage to release an image gen model that's an objective improvement, lets say 80% as good as dalle3, it will be subscription API only.
Are you serious?
I'm using Stability in production: they kept their SDXL beta model which was capable of SDXL 1.0 level prompt adherence at a fraction of the cost up for months after was reasonable for a one-off undocumented beta, and it was a huge boon to my product.
Then a few weeks back they went and quietly cut costs to 1/5th or so what they were for SDXL and released a model that produced similar quality outputs to SDXL for my specific usecase in a fraction of the time (SD 1.6)
They're on fire as far as I'm concerned, just quietly making their product cheaper and faster.
—
Also Dalle 3 is in a very awkward place for programmatic access, so awkward I wouldn't call them competitive to SD for many usecases: It's got a layer of prompt interference baked in, it's expensive, latency is not very consistent. Text is a cool trick but it's still not reliable enough to expose as a core part of the generation for an end user.