The Engine Room, ComfyUI

Every image of our presenter, every video, every daily short comes out of one free app on one PC. This hub is the Engine Room series and everything around it, start with ComfyUI From Zero, then work through editing, video, upscaling, 3D, and the full character pipeline. The companion episodes are on YouTube.

A reference image with a red circle drawn on it beside a long paragraph of prompt text, the circle clearly winning

A Red Circle Beats a Paragraph: People Are Directing AI Models by Drawing on the Input

Two separate finds landed today that work the same way. Draw a red circle on a reference image and the video happens there. Put a red dot where you want the eyes to look and they look there. Our own best result last week was the same idea in a different channel, and it explains why so much prompt wording does nothing.

A closed door in a wall with a small paper form beside it, and the same door standing open

We Got the MiniMax H3 Licence Wrong. So We Applied for It, and Three Days Later We Had Permission.

On 30 August we told you the licence was a gate rather than a ban. That was not right, and the version we corrected away from was closer to the truth. Here is what the licence actually says, what applying took, and the one clause that should stop a lot of people in this hobby cold.

The DIY AI Brief, Ep. 10, Every Wall Became a Policy

Week of 7 September: Linus Torvalds credits an AI in a kernel commit while Debian votes on whether that should be allowed, a local model rebuilds Adobe’s closed DNG format from the bytes up, a company starts selling models with the safety layer removed (the technique is called abliteration, and a paper measured what it costs), World Labs ships Atlas behind a partner gate, and stolen AI session cookies turn out to be doors into work inboxes that no administrator can close.

The AI Image Generator Rematch: Krea 2, Qwen Image, and 20 Generators on One Card

Twenty generators, eight prompts with invented specifics, one shot each, the prompt on every board. New this round: five Krea 2 builds, Qwen Image 2512, a real cloud column priced in Buzz, and a text ladder scored over four extra seeds. Every board at full size, every prompt in all three styles.

A single consumer graphics card driving a video model that produces both picture and sound

MiniMax H3 on One Gaming Card: Five Findings From a Day of Tests

We ran MiniMax H3 for a full day on a single RTX 5090: talking shots driven by our own voice track, a walk and talk, text to speech, a trained voice, and an eight scene short film with its own soundtrack. Every number here came off our machine. So did the mistakes.

Remotion Mastery: Free Motion Graphics From a Local AI Agent, Synced to Every Word

The full build behind EP39: three install commands, a reference generated from the installed packages so the agent stops guessing, motion tokens, word-synced components, cams and graphics trading places on sentence beats, which local model writes the graphics, and the six things that went wrong on the way.

A node graph with one connection broken by a mismatched dependency version, and a single small part restoring it

Your ComfyUI Video Nodes Vanished After an Update. Here Is the One Line That Brings Them Back.

If your LTXVideo nodes stopped loading after updating ComfyUI, you did not break anything. A dependency called kornia gets pulled forward to 0.8.3 and the video node pack cannot import against it. The fix is one command, the issue has been open since June, and there is a real trade-off nobody mentions.

Let Your AI Agent Make the Motion Graphics: Remotion, Word-Synced, Free, on Your Own Machine

How our graphics know the exact frame a word is spoken. A free, local motion-graphics kit built on Remotion, driven by Whisper word timestamps, written by an AI agent from a plain text kit. What we installed, what we built, the model that wrote the props in half a second, and the three things that went wrong.

86 Failures in One Published Episode: What Goes Wrong Making AI Video on One RTX 5090

A published episode scored 86 failures against its own script. Here is every class of mistake we found making local AI video with LTX 2.5, SageAttention, Krea 2 and ComfyUI, what actually caught each one, and the checks we now run before anything ships.

A single model repository at the centre with hundreds of community forks and variants radiating outward across a dark grid

Five Weeks, 400 Repositories: What Happens When Everyone Gets the Weights

Hugging Face says MiniMax H3 went up on 28 July. Five weeks later there are around 400 repositories with its name on them, new ones arriving at eight to twenty-four a day, and this week the community visibly stopped asking whether it runs and started asking how fast. Here is what that pace actually looks like, and why our own pipeline is not moving anywhere near that quickly.