Divam Gupta (@divamgupta) / X

Divam Gupta

302 posts

Divam Gupta

@divamgupta

Building @Stellon_Labs (YC S25) - tiny AI models that (hopefully) think • Past: ml research @Meta, @Microsoft, @CarnegieMellon, @DiffusionBee

San Francisco, CA

Joined June 2011

Pinned
Divam Gupta
@divamgupta
Feb 19
We just released a new version of Kitten TTS - 15M param SOTA tiny text-to-speech model It has a significant quality improvement over the previous version. Still less than 25MB in size! Open-source, extremely tiny, expressive. github.com/KittenML/Kitte… Apache 2.0
00:00
Divam Gupta
@divamgupta
Aug 5, 2025
Introducing Kitten TTS, a SOTA tiny text-to-speech model - Just 15M parameters - Runs without a GPU - Model size less than 25 MB - Multiple high-quality voices - Ultra-fast - even runs on low-end edge devices Github and HF links below
00:00
Divam Gupta
@divamgupta
Sep 11, 2022
Introducing Diffusion Bee, the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed. Link : github.com/divamgupta/dif…
Divam Gupta
@divamgupta
Sep 28, 2023
Exciting news! Our team worked to make this a reality - first photorealistic podcast in VR feat. @lexfridman This podcast was entirely hosted in VR, with realistic avatars generated through machine learning. The immersive experience truly transports you, making it feel as if
00:00
Divam Gupta
@divamgupta
Aug 6, 2025
We launched on possibly the worst timing ever - right when OpenAI, Google DeepMind, and Anthropic all had major releases. Somehow we still made it to #1 on Hacker News. Thanks to everyone who checked us out! 🙏
Divam Gupta
@divamgupta
Sep 17, 2022
Stable Diffusion implemented using @Tensorflow and #Keras. - Converted pre-trained models - Easy to understand code - Minimal code footprint Code : github.com/divamgupta/sta… Google Colab with @Gradio demo : colab.research.google.com/drive/1fBlfPsL…
Divam Gupta
@divamgupta
Nov 3, 2022
Introducing a new version of DiffusionBee - Stable Diffusion app on Mac with all cutting-edge features. - Easy to use and install - Runs locally - Runs much faster now Supports Text-to-image, Image-to-image, in-painting, out-painting, advanced options. diffusionbee.com
00:00
Divam Gupta
@divamgupta
Nov 1, 2022
DreamBooth is becoming popular for creating custom Stable Diffusion models using your images. Here is a beginner friendly thread on how it works: 🧵
Divam Gupta
@divamgupta
Oct 21, 2022
It’s been 2 months since Stable Diffusion’s release, it has been re-implemented in almost every popular ML framework out there. Here are some popular implementations: 🧵 :
Divam Gupta
@divamgupta
Aug 5, 2025
The open-source community is amazing. We released a tiny TTS model under 25MB. And someone made a web-browser demo within few hours. Yes, its running locally in the web-browser Thanks clowerweb!
00:00
Divam Gupta
@divamgupta
Sep 30, 2022
Image2Image is now available in Tensorflow / Keras version of Stable Diffusion. Repo link : github.com/divamgupta/sta… Colab link : colab.research.google.com/drive/1gol0M61…
Divam Gupta
@divamgupta
Jan 28, 2023
Most AI image generation tools include an invisible watermark in the generated image. This watermark is invisible to human eyes, but can be identified by the algorithm 🧵.
Divam Gupta
@divamgupta
Aug 9, 2025
I've left Meta Reality Labs. Miss working with the best team for realistic avatars. Damn, I definitely miss using thousands of GPUs and running super large-scale training experiments. Now back to being GPU poor, but excited to start something new: building tiny AI models for
Divam Gupta
@divamgupta
Sep 25, 2022
Last week I implemented Stable Diffusion using Keras / Tensorflow. Now its almost integrated in KerasCV thanks to @fchollet and team. This is the power of open source collaboration.