# ComfyUI: what I've logged

> ComfyUI comes up in 2 posts of my AI log, from October 2026 to October 2026, and each item below links to the primary source. I filed it under open weights, image, video, world and agents and coding.

## Items

1. **ComfyUI-Drama3** (PedroMarinhoDev, 16 Oct 2026): The Drama 3 text-to-speech pack for ComfyUI says it is about 3x faster since 17 October, with a 9 s line on an RTX 4090 taking 3.9 s instead of 13.6 s. [Primary source](https://github.com/PedroMarinhoDev/ComfyUI-Drama3) · [Post](https://heyaliasif.com/ai/2026-10-17-nvidia-dory-llmspeed-moss-8-step-drama3#item-4)
2. **Nvidia VFX Nodes for Video Upscaling, Frame Generation and SDR-to-HDR** (ComfyUI, 13 Oct 2026): RTX super resolution, frame generation and SDR-to-HDR now run as local ComfyUI nodes that can be chained in one workflow. [Primary source](https://blog.comfy.org/p/nvidia-vfx-nodes-for-video-upscaling) · [Post](https://heyaliasif.com/ai/2026-10-14-gemini-4-argon-lfm-runai#item-5)

## Posts

- 2026-10-17 [NVIDIA's looped Dory, Llmspeed, MOSS in 8 steps, Drama 3 faster](https://heyaliasif.com/ai/2026-10-17-nvidia-dory-llmspeed-moss-8-step-drama3)
- 2026-10-14 [Gemini 4 Argon lands, Run:ai goes open source](https://heyaliasif.com/ai/2026-10-14-gemini-4-argon-lfm-runai)

Canonical: https://heyaliasif.com/ai/topics/comfyui