r-k-jo

Joined 10 years ago

Karma

Submissions

Member since

Dec 3

Recent submissions

You can also target WASM. Depending on the model size, it can be really good. Here are some examples of quantized models.

Vision Model https://huggingface.co/spaces/radames/Candle-Moondream-2 Blip Image Captioning https://huggingface.co/spaces/radames/Candle-BLIP-Image-Capt... Microsoft Phi 2 https://huggingface.co/spaces/radames/Candle-phi1-phi2-wasm-...

Google MusicFX DJ Mode aitestkitchen.withgoogle.com

4 r-k-jo 2 years ago 1 comments

Comment · 2 years ago

Clipper.js is built on top of Mozilla's Readability library, Turndown to convert HTML to Markdown https://github.com/philschmid/clipper.js

Comment · 2 years ago

It's using ~15GB VRAM

Comment · 2 years ago

I also made a demo with Gradio, but it's 2x slower than fal.ai! Using stable-fast compilation running on a single A10G

https://huggingface.co/spaces/radames/Real-Time-Text-to-Imag...

I you have GPU/cuda/Docker you can try it locally

docker run -it -p 7860:7860 --platform=linux/amd64 --gpus all -e SFAST_COMPILE="1" -e USE_TAESD="0" registry.hf.space/radames-real-time-text-to-image-sdxl-lightning:latest python app.py

AI Tube jbilcke-hf-ai-tube.hf.space

2 r-k-jo 2 years ago 0 comments

Comment · 3 years ago

Here is a collection of demos with fast LCM on HuggingFace

https://huggingface.co/collections/latent-consistency/latent...

Comment · 3 years ago

yes, just publish it on the readme.me here https://github.com/radames/Real-Time-Latent-Consistency-Mode...

Comment · 3 years ago

Hi, I've built the demo. Unfortunately, it's running on a single GPU and can only be used concurrently by a few users. For a better real-time experience, you would need a dedicated machine.

You can get the source here and how to run: https://github.com/radames/Real-Time-Latent-Consistency-Mode... See video here: https://twitter.com/radamar/status/1718783886413709542 or on the Github readme.

FYI, this is made possible due to a new technique: https://latent-consistency-models.github.io, fine-tuning an existing models. The author will soon publish the training script. We'll see all the cool image models running at this speed! I'm excited for this! I can see many interesting experiments and projects emerging from this.