[HN Gopher] AI model for near-instant image creation on consumer...
___________________________________________________________________
AI model for near-instant image creation on consumer-grade hardware
Author : giuliomagnifico
Score : 103 points
Date : 2024-12-10 16:44 UTC (6 hours ago)
(HTM) web link (www.surrey.ac.uk)
(TXT) w3m dump (www.surrey.ac.uk)
| Sharlin wrote:
| For those wondering, it's an adversarially distilled SDXL
| finetune, not a new base model.
| throwaway314155 wrote:
| Thanks! This article is pretty heavy with PR bullshit.
| quikoa wrote:
| Github: https://chendaryen.github.io/NitroFusion.github.io/
|
| Paper: https://arxiv.org/html/2412.02030v2
| betenoire wrote:
| Here is the demo
| https://huggingface.co/spaces/ChenDY/NitroFusion_1step_T2I
|
| I'm unable to get anything that looks as good as the images in
| the README, what's the trick for good image prompts?
| speerer wrote:
| I always just assume it's the magic of selection bias.
| avereveard wrote:
| I get pretty close result with seed 0
|
| paper https://i.imgur.com/l90WYrT.png
|
| replication on hf https://i.imgur.com/MqN1Qwc.png
| betenoire wrote:
| the imgur link is bad, but I hadn't noticed the prompt tucked
| away in those reference images and that helps. Thanks
|
| (I had asked for a rock climber dangling from a rope, eating
| a banana, and they were wildly nonsensical images)
| deckar01 wrote:
| I had the same issue, so I pulled in the SDXL refiner. Night
| and day better even at one step.
|
| https://gist.github.com/deckar01/7a8bbda3554d5e7dd6b31618536...
| betenoire wrote:
| thank you!
| nprateem wrote:
| The devil's in the details as always. A "cartoon of a cat eating
| an icecream on a unicycle" doesn't bring back any of the 6-pawed
| mutant cats riding a unicycle, etc. Still, impressive speed.
| iLoveOncall wrote:
| > Instant image generation that responds as users type - a first
| in the field
|
| Stable Diffusion Turbo has been able to do this for more than a
| year, even on my "mere" RTX 3080.
| tgsovlerkhgsel wrote:
| The models seem to have gotten to a point where even something I
| can run locally will give decent results in a reasonable time.
| What is currently "the best" (both from an output quality and
| ease of installation perspective) setup to just play with local
| a) image generation, b) image editing?
| LeoPanthera wrote:
| If you have a Mac, get "Draw Things":
| https://drawthings.ai/releases/
|
| It supports all major models and has a native Mac UI, and as
| far as I can tell there's nothing faster for generation.
|
| The "best" models, and a bunch more, are built-in. The state of
| the art is FLUX.1, "dev" version for quality, "schnell" version
| for speed.
|
| SDXL is an older, but still good model, and is faster.
| LZ_Khan wrote:
| Edit: never mind seems like this recommendation is not the best
|
| A1111 is a good place to start. Very beginner friendly UI. You
| can lookup some templates on Runpod to get started if you don't
| have a GPU.
|
| someone else mentioned a local setup which might be even easier
| 42lux wrote:
| A1111 is EoL.
| qclibre22 wrote:
| git clone https://github.com/lllyasviel/stable-diffusion-webui-
| forge.g...
|
| download models and _all_ vae files for the model, put in right
| place, run batch file, configure correctly and then gen images
| using browser.
| ajdjspaj wrote:
| What does consumer-grade mean in this context - is this referring
| to an M1 MacBook or a tower full of GPUs? I couldn't find in the
| paper or README.
___________________________________________________________________
(page generated 2024-12-10 23:00 UTC)