Thanks for the summary,
@Sentdex
!
For the curious, there are some examples on their GitHub repo https://github.com/KindXiaoming/pykan
Radamés Ajna
radames
AI & ML interests
None yet
Organizations
radames's activity
Hi @renyuxi , thanks for sharing this update! 8 steps with CFG and negative prompts is amazing!
posted
an
update
4 days ago
Post
1591
I've built a custom component that integrates Rerun web viewer with Gradio, making it easier to share your demos as Gradio apps.
Basic snippet
More details here radames/gradio_rerun
Source https://github.com/radames/gradio-rerun-viewer
Follow Rerun here https://huggingface.co/rerun
Basic snippet
# pip install gradio_rerun gradio
import gradio as gr
from gradio_rerun import Rerun
gr.Interface(
inputs=gr.File(file_count="multiple", type="filepath"),
outputs=Rerun(height=900),
fn=lambda file_path: file_path,
).launch()More details here radames/gradio_rerun
Source https://github.com/radames/gradio-rerun-viewer
Follow Rerun here https://huggingface.co/rerun
replied to
oliveryanzuolu's
post
10 days ago
amazing work @oliveryanzuolu 👏 Do you have plans to release the training distillation code?
posted
an
update
11 days ago
Post
2238
ByteDance released new distillation technique Hyper-SD (
ByteDance/Hyper-SD) for efficient image generation.
Here a few demos:
Official:
Hyper-SDXL-1Step-T2I ByteDance/Hyper-SDXL-1Step-T2I
Hyper-SD15-Scribble ByteDance/Hyper-SD15-Scribble
Unofficial Demos: InstantStyle + Hyper SD1.5 (not great but super fast) radames/InstantStyle-Hyper-SD
InstantStyle + Hyper SDXL radames/InstantStyle-Hyper-SDXL
Here a few demos:
Official:
Hyper-SDXL-1Step-T2I ByteDance/Hyper-SDXL-1Step-T2I
Hyper-SD15-Scribble ByteDance/Hyper-SD15-Scribble
Unofficial Demos: InstantStyle + Hyper SD1.5 (not great but super fast) radames/InstantStyle-Hyper-SD
InstantStyle + Hyper SDXL radames/InstantStyle-Hyper-SDXL
posted
an
update
11 days ago
Post
2141
InstantStyle works with the 2-step SDXL-Lightning distilled model, reducing generation time from ~20s to ~9s!
In a big related update, as of today, Diffusers@main supports InstantStyle. I'm looking forward to playing with it!
https://github.com/huggingface/diffusers/pull/7668
radames/InstantStyle-SDXL-Lightning
ByteDance/SDXL-Lightning
In a big related update, as of today, Diffusers@main supports InstantStyle. I'm looking forward to playing with it!
https://github.com/huggingface/diffusers/pull/7668
radames/InstantStyle-SDXL-Lightning
ByteDance/SDXL-Lightning
replied to
andrewrreed's
post
11 days ago
Very interesting, @andrewrreed , and completely unaware of this feature! Do you know of any other strategies for grounded generation in models like LLaMA or Mistral?
posted
an
update
20 days ago
Post
3815
Here's a utility component for integrating your Gradio app with Hugging Face. This custom component enables you to search for models, spaces, datasets, and users.
You can see it in action here. arcee-ai/mergekit-config-generator
And learn how to use it here radames/gradio_huggingfacehub_search
pip install gradio_huggingfacehub_searchYou can see it in action here. arcee-ai/mergekit-config-generator
And learn how to use it here radames/gradio_huggingfacehub_search
posted
an
update
about 1 month ago
Post
2720
Following up on
@vikhyatk
's Moondream2 update and
@santiagomed
's implementation on Candle, I quickly put togheter the WASM module so that you could try running the ~1.5GB quantized model in the browser. Perhaps the next step is to rewrite it using https://github.com/huggingface/ratchet and run it even faster with WebGPU,
@FL33TW00D-HF
.
radames/Candle-Moondream-2
ps: I have a collection of all Candle WASM demos here radames/candle-wasm-examples-650898dee13ff96230ce3e1f
radames/Candle-Moondream-2
ps: I have a collection of all Candle WASM demos here radames/candle-wasm-examples-650898dee13ff96230ce3e1f
replied to
freddyaboulton's
post
about 1 month ago
nice!! can you set the jpeg quality as well?
thanks @chansung this is so helpful! btw you could launch a quantize version here https://huggingface.co/spaces/chansung/gradio_together_tgi/blob/main/entrypoint.sh.template#L11 and even try running this on CPU.
@Wauplin is doing impressive work here. 👏
posted
an
update
about 1 month ago
Post
3470
Testing new pix2pix-Turbo in real-time, very interesting GAN architecture that leverages SD-Turbo model. Here I'm using edge2image LoRA single-step inference 🤯
It's very interesting how ControlNet Canny quality is comparable, but in a single step. Looking forward to when they release the code: https://github.com/GaParmar/img2img-turbo/issues/1
I've been keeping a list of fast diffusion model pipelines together with this real-time websocket app. Have a look if you want to test it locally, or check out the demo here on Spaces.
radames/real-time-pix2pix-turbo
Github app:
https://github.com/radames/Real-Time-Latent-Consistency-Model/
You can also check the authors img2img sketch model here
gparmar/img2img-turbo-sketch
Refs:
One-Step Image Translation with Text-to-Image Models (2403.12036)
cc @gparmar @junyanz
It's very interesting how ControlNet Canny quality is comparable, but in a single step. Looking forward to when they release the code: https://github.com/GaParmar/img2img-turbo/issues/1
I've been keeping a list of fast diffusion model pipelines together with this real-time websocket app. Have a look if you want to test it locally, or check out the demo here on Spaces.
radames/real-time-pix2pix-turbo
Github app:
https://github.com/radames/Real-Time-Latent-Consistency-Model/
You can also check the authors img2img sketch model here
gparmar/img2img-turbo-sketch
Refs:
One-Step Image Translation with Text-to-Image Models (2403.12036)
cc @gparmar @junyanz
replied to
visheratin's
post
2 months ago
hi @visheratin , do you have any guides on how to train similar model? Phi-2 + SigLIP vision encoder?
very cool! I just ordered RPi5 to run some tests, also this awesome mic hat
I know it's possible to run real-time whisper on a rapberrypi with whisper.cpp @ggerganov
Are you thinking of running it on a device or in the cloud?
hello 👋