Migrating from Grav to Hugo
Due to issues with updating PHP on my shared hosting which I cannot be bothered to resolve, I am now considering migrating from Grav to Hugo. ...
Ai
Chatterbox Turbo TTS with MLX-Audio
In my last post, I tried Qwen3-TTS… This time, I test Chatterbox Turbo by Resemble.ai, which is an open-source, MIT licensed, text-to-speech model with zero-shot cloning. ...
Qwen3-TTS with MLX-Audio on macOS
Alibaba’s Qwen3-TTS for Speech Synthesis (text-to-speech) was open-sourced (Apache-2.0) on 22 Jan 2026. And within the last couple of weeks, we now have Apple Silicon optimization via MLX-Audio. Here is code to create an audiobook from an ePub. ...
Reflections on 2025 through the Word(s) of the Year
In March 2025, I posted an opinion piece entitled “My Disillusionment with Generative AI”. Things have gotten worse since then, to the extent that “Slop” and “AI Slop” have been picked as the Word(s) of the Year for 2025. What follows are my thoughts on the trajectory of technology and, more specifically, AI, as reflected in the Word(s) of the Year (WOTY). ...
Kokoro TTS and Abogen on Windows
In my last post, I described trying out Kokoro text-to-speech (TTS) model via Kokoro-FastAPI web UI in a macOS (native) container. Here, I install Kokoro-TTS and Abogen on Windows, to take advantage of my Nvidia GPU. ...
Running Kokoro TTS via macOS Containerisation Framework
A short 2-in-1 post of two things I’ve been meaning to try out on macOS - first, to try the new macOS Container framework on macOS 15.5… and second, to spin up Kokoro Text-to-Speech (TTS) in a container. ...
My Disillusionment with Generative AI
I’m a techno optimist by default, I do believe technology can solve the problems we face today, and make our lives better. But I do have concerns with the direction we are taking with Generative AI, and the future we are heading towards. This is an opinion piece… ...
Using Flux.1 in GGUF format on macOS
city96 has published GGUF versions of the Flux1.Dev model and T5 XXL text encoder, along with custom nodes to use them in ComfyUI - thought I’d try them on my M2 Mac mini, hoping for faster inference! ...
Faster Flux.1
More Flux.1-based models! Go faster with FP8 or NF4! New LoRAs and ControlNets! There is quite a bit of interest with this model, as evidenced by the speed of community-led enhancements. ...
Wow! Flux.1 by Black Forrest Labs
While I have many posts about SDXL, I do not use Stable Diffusion 3 at all - license concerns aside, it is simply not good, and may never get better. But just a few days ago, a new, freely available, offline model that is better than SDXL was released by the team that presented Latent Diffusion and created Stable Diffusion, Flux.1 by Black Forrest Labs! ...