ComfyUI Blog
blog.comfy.org · Company blog · on HN since 2024
The official blog of ComfyUI, a node-based tool for running image and video generation models, covering releases, model support and funding.
What HN saysHN links it for model support announcements and funding details; one commenter notes it is VC-backed, and another says its pipeline approach resembles other tools.
15HN people shared it
4linked it in comments
12stories submitted
74story points
3 months agolast shared
2024people per year2026
Most-shared posts
- 1MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video2 people · 28 points · first shared 2026 · 4 comments on HN
- 2ComfyUI V1: a seamless desktop experience for ComfyUI1 people · 20 points · first shared 2024 · 3 comments on HN
- 3ComfyUI supports masking and scheduling of LoRA and model weights1 people · 5 points · first shared 2024 · 2 comments on HN
- 4ComfyUI Now Supports Stable Diffusion 3.51 people · 4 points · first shared 2024 · discussion on HN
- 5Running Mochi (SOTA video generation) in ComfyUI on one 4090 GPU1 people · 3 points · first shared 2024 · 1 comments on HN
- 6ComfyUI Raises $30M1 people · 3 points · first shared 2026 · discussion on HN
- 7Wan 2.2 in ComfyUI1 people · 2 points · first shared 2025 · 1 comments on HN
- 8Flux.1 Kontext [Dev] Day-0 Support in ComfyUI1 people · 2 points · first shared 2025 · discussion on HN
- 9ComfyUI on Nvidia DGX Spark1 people · 2 points · first shared 2025 · discussion on HN
- 10ComfyUI statement on the Ultralytics crypto miner situation1 people · 2 points · first shared 2024 · discussion on HN
- 11Dynamic VRAM in ComfyUI: Saving Local Models from RAMmageddon1 people · 2 points · first shared 2026 · discussion on HN
- 12Comfy.org1 people · 1 points · first shared 2026 · discussion on HN
- 13Nano banana via comfyui api nodes1 people · first shared 2025
- 14Comfy raises 17m funding1 people · first shared 2026
What HN people wrote when they linked it
peter_d_sherman · 2026-08-03
>"FP8, which has been used as the standard until now, was only supported by the RTX 40/50 series.
In contrast,
INT8 ConvRot
is attracting attention because it can benefit from hardware support even on the RTX 20/30 series."
Related:
https://blog.comfy.org/p/minimax-h3-day-0-support-in-comfyui
homarp · 2026-02-22
>ComfyUI [...] none are VC-backed SaaS
https://blog.comfy.org/p/comfy-raises-17m-funding
"with $17 million in funding from world-class investors such as Pace Capital, Chemistry, Abstract Ventures and many others"
ch4s3 · 2025-09-10
I'm looking at their blog[1] and yeah it looks like they're doing literally the exact same thing the other tools I named are doing but with a UI inspired by things like shader pipeline tools in game engines. It isn't clear how it's doing all of the things the grandparent is claiming.
[1]https://blog.comfy.org/p/nano-banana-via-comfyui-api-nodes
dragonwriter · 2024-10-22
Some notes/resources:
* Unlike the Stable Diffusion 3.0 release, where the public release was initially (and ultimately only) the Medium model, this is both the base and distilled (fewer steps needed) Turbo versions of the Large model (8B).
* ComfyUI has immediate support for SD3.5 Large [0], and comfy.org has released an FP8 scaled version of the model [1] for lower memory use (note that the FP8 version is almost as large in file size as the base FP16 model, but that's because it has the 3 text encoders baked in, while the base model relies on them being distributed separately.)
* Even smaller bitsandbytes nf4 version [2]
* Some SD3.5 LoRAs already released. [3][4][5]
* Fine-tuning guide. [6]
[0] https://blog.comfy.org/sd3-5-comfyui/
[1] https://huggingface.co/Comfy-Org/stable-diffusion-3.5-fp8/tree/main
[2] https://huggingface.co/sayakpaul/sd35-large-nf4
[3] https://huggingface.co/Shakker-Labs/SD3.5-LoRA-Chinese-Line-Art
[4] https://huggingface.co/Shakker-Labs/SD3.5-LoRA-Linear-Red-Light
[5] https://huggingface.co/Shakker-Labs/SD3.5-LoRA-Futuristic-Bzonze-Color… (don't ask me why it is "bzonze" and not "bronze".)
[6] https://stabilityai.notion.site/Stable-Diffusion-3-5-Large-Fine-tuning…