|
| Der_Einzige wrote:
| The fact that LCM loras turn regular SD models into psudo-LCM
| models is insane.
|
| Most people in the AI world don't understand that ML is like
| actual alchemy. You can merge models like they are chemicals. A
| friend of mine called it "a new chemistry of ideas" upon seeing
| many features in Automatic1111 (including model and token merges)
| used simultaneously to generate unique images.
|
| Also, loras exist on a spectrum based on their dimensionality.
| Tiny loras should only be capable of relatively tiny changes. My
| guess is that this is a big lora, nearly the same size as the
| base checkpoint.
| keonix wrote:
| Wait until you hear about frankenmodels. You rip parts of one
| model (often attention heads) and transplant them in another
| and somehow that produces coherent results! Witchcraft
|
| https://huggingface.co/chargoddard
| GaggiX wrote:
| >somehow that produces coherent results
|
| with or without finetuning? Also is there a practical
| motivation for creating them?
| keonix wrote:
| > with or without finetuning?
|
| With, but it's still bonkers that it works so well
|
| >Also is there a practical motivation for creating them?
|
| You could get in-between model sizes (like 20b instead of
| 13b or 34b). Before better quantization it was useful for
| inference (if you are unlucky with vram size), but now I
| see this being useful only for training because you can't
| train on quants
| GaggiX wrote:
| lcm-lora-sdv1-5 is 67.5M, lcm-lora-sdxl is 197M, so they are
| much smaller than the entire model, would be cool to check the
| rank used with these LoRAs tho
| liuliu wrote:
| 64.
| temp72840 wrote:
| This is nuts. I did a double take at this comment - I thought
| you _must_ have been talking about LoRAing a LCM distilled from
| Stable Diffusion.
|
| LCMs are spooky black magic, I have no intuitions about them.
| ttul wrote:
| When I was taking Jeremy Howard's course last fall, the
| breakthrough in SD was going from 1000 steps to 50 steps via
| classifier-free guidance, which is this neat hack where you
| run inference with your conditioning and without and then mix
| the result. To this day I still don't get it. But it works.
|
| Now we find this way to skip to the end by building a model
| that learns the high dimensional curvature of the path that a
| diffusion process takes through space on its way to an
| acceptable image, and we just basically move the model along
| that path. That's my naive understanding of LCM. Seems to
| good to be true, but it does work and it has a good
| theoretical basis too. Makes you wonder what is next? Will
| there be a single step network that can train on LCM to
| predict the final destination? LoL that would be pushing
| things too far..
| hadlock wrote:
| Sounds like we've invented the kind of psychic time travel
| they use in Minority report. Let me show you right over to
| the Future Crimes division. We're arresting this guy making
| cat memes today because the curve of his online history
| traces that of a radicalized blah blah blah
| ttul wrote:
| To me, the crazy thing about LoRA is they work perfectly well
| adapting models checkpoints that were themselves derived from
| the base model on which the LoRA was trained. So you can take
| the LCM LoRA for SD1.5 and it works perfectly well on, say,
| RealisticVision 5.1, a fine-tuned derivative of SD1.5.
|
| You'd think that the fine tuning would make the LCM LoRA not
| work, but it does. Apparently the changes in weights introduced
| through even pretty heavy fine tuning does not wreck the
| transformations the LoRA needs to make in order to make LCM or
| other LoRA adaptations work.
|
| To me this is alchemy.
| yorwba wrote:
| Finetuning and LoRAs both involve additive modifications to
| the model weights. Addition is commutative, so the order in
| which you apply them doesn't matter for the resulting
| weights. Moreover, neural networks are designed to be
| differentiable, i.e. behave approximately linearly with
| respect to small additive modifications of the weights, so as
| long as your finetuning and LoRA change the weights only a
| little bit, you can finetune with or without the LoRA,
| respectively train the LoRA on the finetuned model or its
| base, and get mostly the same result.
|
| So this is something that can be somewhat explained using not
| terribly handwavy mathematics. Picking hyperparameters on the
| other hand...
| smusamashah wrote:
| Ok. I have seen the term LCM Lora a number of times. I have
| used both stable Diffusion and LORAs for fun for quite a while.
| But I always thought this LCM Lora is a new thing. It's simply
| not possible using current samplers to return an image under 4
| steps. What you are saying is that just by adding a Lora we can
| get existing models and samplers to generate a good enough
| image in 4 steps?
| jyap wrote:
| Yes check out this blog post:
| https://huggingface.co/blog/lcm_lora
|
| I've used it with my home GPU. Really fast which makes it
| more interactive and real-time.
| catwell wrote:
| It's a different sampler too.
| jimmySixDOF wrote:
| And here is a demo mashed up using LeapMotion free space hand
| tracking and a projector to manipulate a "bigGAN's high-
| dimensional space of pseudo-real images" to make it more like a
| modern dance meets sculpting meets spatial computing with a hat
| tip to the 2008 work of Johnny Chung Lee while at Carnage Mellon.
|
| https://x.com/graycrawford/status/1100935327374626818
| smlacy wrote:
| https://nitter.net/abidlabs/status/1723074108739706959
| r-k-jo wrote:
| Here is a collection of demos with fast LCM on HuggingFace
|
| https://huggingface.co/collections/latent-consistency/latent...
___________________________________________________________________
(page generated 2023-11-12 23:00 UTC) |