The source code for DragGAN has been released! Huge thanks to community contributor LeoXing1996 for the @Gradio demo
try it now:
huggingface.co/spaces/radames…
00:00
Radamés Ajna
2,457 posts
Radamés Ajna
@radamar
San Francisco Bay Area
Joined January 2009
- Every day, there's a new exciting paper demo on the hub, it's hard to keep up! New AI video-to-video translation huggingface.co/spaces/Anonymo…
00:00 - Thanks to the Latent Consistency Model (LCM), we're nearing real-time image diffusion. I've made a simple MJPEG server for generation stream using diffusers img2img pipeline. It's really fun to play with it. Can't wait for the ControlNet version. try it: huggingface.co/spaces/radames…
00:00 - I've made it possible to share you're screen on the real-time Latent Consistency Model demo, thanks to Screen Capture Web API! No need for a custom drawing tool, use your favorite one 🤩. Plus, enjoy musk rickrolling demo: huggingface.co/spaces/radames…
00:00 - Create sentence embeddings in your browser with transformers.js! My guide walks you through generating embeddings and applying UMAP dimension reduction + more - all in JavaScript, no server needed observablehq.com/@huggingface/s…
00:00 - Great news! The @huggingface hub now has the first QR code AI art generator. You only need the QR Code content and a text-to-image prompt idea, or you can upload your image! Check it out! huggingface.co/spaces/hugging…
- Just added ControlNet Canny to the near real-time Latent Consistency Model demo. It's much better than just img2img! Any updates to the UI parameters and prompts happen instantly. Video here at 2x speed Demo: huggingface.co/spaces/radames…
00:00 - InstantID works with ControlNet Pose and LCM, and it might actually work with any ControlNet. The trade-off of using multiple ControlNets results in a slight loss of facial detail.
00:00 - In a couple of weeks, we went from LCM LoRa getting about ~5fps to now ~17fps with the latest SD-Turbo distilled model. Thanks @StabilityAI the quality with SD-Turbo is incredible! Video is at normal speed. see Musk and Gates with curly hair 😅 demo: huggingface.co/spaces/radames…
00:00 - Here is the DragGAN Face Inversion @Gradio demo. You can upload your image and experiment with some wild edits. Please be patient, as the inversion training process takes approximately 2 minutes 😞 huggingface.co/spaces/DragGan…
00:00 - Here's the demo "Enhance This"! It's a surreal image magnifier that creates a high-res version by imagining new details, using the SDXL base model. Thanks to @RuoyiDu's DemoFusion research. It takes a ~minute to generate a 2024x2024 image. huggingface.co/spaces/radames…
00:00 - I've also put together a text-to-image version so you can get a sense of what it's like to live-prompt a model, thanks to Latent Consistency Model speed. btw I'm not good at prompting. Video is at 4x, as my typing isn't fast. here: huggingface.co/spaces/radames…
00:00 - Check out a new ControlNet face model on the hub by @JCatrambone & @DarthMarkov, trained on the LAION-Face dataset it works with multiple faces. I've updated the live conditioning @Gradio component, try the official demo here huggingface.co/spaces/Crucibl…
00:00 - I made a custom @Gradio component to generate face landmarks conditioning image for the ControlNet Uncanny Faces model try the live demo here huggingface.co/spaces/pcuenq/…
00:00
