Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
Last night, @higgsfield sent @ComfyUI a cease and desist (attached)
They want the Open Source Higgsfield challenge taken down within 48 hours.
Their argument is that our use of the Higgsfield name and that using their CEO's likeness is an infringement violation (man, the irony). Claiming that it makes the event look like Higgsfield is associated with it.
This couldn't be farther from the truth, which is that Higgsfield made a promise to open source its product and never did.
For the past two weeks, builders have been recreating popular closed apps as open workflows anyone can run.
So we asked our community to deliver where Higgsfield failed: apps in the open, built by the community, for the community. We've made it clear that the challenge is organized by ComfyUI and not affiliated with or endorsed by Higgsfield.
When we started Comfy, we made the community a promise. Our product stays open, free, and yours. We’ve kept it every day since, and one letter isn’t going to change that.
The challenge stays up. Comfy and open source will win!
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
Regenerate Minimax H3 videos in 2K in just 3 steps. It does tend to change details and faces though.
github.com/NVlabs/Sana/tree/…
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
Your X links are snitching on you.
- s=46 means iPhone
- s=20 means desktop
Some people now see an "a=" code too, reportedly tied to their account.
Delete everything after the "?" before you share.
Example below 👇
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
▼概要
動画生成モデル「MiniMax H3」向けの構造化プロンプトを構築できるComfyUIカスタムノード「Ultra MiniMax H3 Prompt」が公開。
▼ポイント
・通常生成(T2V/I2V等)と参照生成(R2V)に対応した2種類の独立したノードを提供
・最大3人の人物設定や最大6つの時系列イベント(カメラ、セリフ、音響など)をメニュー選択と入力で指定可能
・LLMやVLMを使わず、ルールベースで入力条件の検証とH3向けプロンプトの整形を実行
・追加のpipパッケージ不要で導入可能
▼使い所
カメラワークや複数人のセリフ進行など、MiniMax H3で複雑な時間変化を伴う映像指示を手動で英語記述せず体系的に設計したい場面で有効。
#MiniMaxH3 #ComfyUI
URLはリプ⬇️
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
NVIDIA open-sourced Open-H3-Regenerate-2K (was API-only). Running it local on my 5090.
Same 768P MiniMax H3 draft → 2560×1440:
- Draft: 2:09
- NVIDIA default: 3:15 · SSIM 0.75 / 0.61
- My tuned: 2:28 · SSIM 0.83 / 0.68
Default = detail monster, but it recasts the face and the Boston Terrier. Tuned keeps identity. First round of settings, more testing coming.
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
MiniMax H3 ref2vaを使った4面キャラクタシート生成Workflow!
civitai.com/models/3022612/m…
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
Generated with Minimax H3 Singularity on Maestro (4 steps), NVIDIA A4500.
Prompt: 15-second anime video. Use the provided image as the exact opening frame. Preserve the original anime style, character design, red shirt, brown shorts, and proportions throughout. One continuous shot. 0–7s: The muscular man carries an enormous nuclear bomb while plummeting toward San Francisco at terrifying speed. The camera follows him from behind as the city approaches rapidly. Violent wind, intense motion blur, epic apocalyptic orchestral music. He screams furiously: "SAN FRANCISCO! YOUR TIME HAS COME!" The streets and buildings rush closer. Everything suggests an imminent catastrophic nuclear impact. 7–9s: Just before hitting the ground, he suddenly looks toward the camera and breaks into an enormous, confident smile. His descent slows as the camera smoothly swings around to face him. He lands on the sidewalk, leaving the enormous bomb standing harmlessly behind him, and immediately begins striding confidently toward the camera. 9–15s: The camera tracks backward as he walks directly toward it, delivering an extremely enthusiastic Silicon Valley startup founder pitch. He makes constant, ridiculously exaggerated hand gestures: pointing both hands at the camera, spreading his arms wide, chopping the air, and leaning forward to emphasize every claim. His energy is obnoxiously confident, like a viral YC startup launch video on X. He speaks like a typical startup bro founder, with absolute sincerity: "For years, startups have promised to disrupt everything. We decided to take that literally. Introducing, Bomb dot AI. We blow up everything." He finishes by spreading both arms triumphantly, beaming at the camera, with the enormous nuclear bomb visible behind him.
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
New way to make massive 6K resolution images. Works for Qwen Image, Ideogram, Flux.
github.com/KooroshRH/AReA
i own a relatively new (2025) samsung tv.
i kept getting weirdly targeted ads.
i tried reversing the firmware but it was aes encrypted and no keys unless tear it apart and do uart/jtag magic.
zero days it is. root shell on new samsung TVs!
discovered PRIVACY HORROR. write up?
Replying to @superalesha
There are other things you can patch on 3090s.
1) For example you can remove the maximum of simultaneous NVENC encoding
github.com/keylase/nvidia-pa…
2) Or the p2p gpu unlock
github.com/aikitoria/open-gp…
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
Confirmed that 3090 unlock is successful
with 360watt power wall, I got 75T -> 135T (measured in Pytorch)
Which is insane
I used github.com/Zagitta/gpu-unloc… with commit a9b0c75
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
Meet Qwen3.5-9B-uncensored-MNN: a 9B model built for on-device AI. Abliterated and uncensored, it runs on mobile via MNN. No cloud needed, just pure local power. 1,090 downloads and counting!
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
動画生成MiniMax H3派生のComfyUIワークフロー「MiniMax H3 REMIX」がv8.0に更新。
画像や音声、動画素材を柔軟に組み替え可能な設計。手足の歪みや動きの硬さを抑えるLoRAを統合し、動画やデジタルヒューマン制作を効率化。
#MiniMaxH3 #ComfyUI
URLはリプ⬇️
Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 retweeted
MOSS Image Edit loras.
Just like how Krea 2 Identity Edit could bring out a image edit model from an image gen model, MOSS Image Edit is here to do the same.
I got to go back and work more with MOSS. It's like Krea 2, but with a much better license.
huggingface.co/chinoll/Moss-…



































