Two posts in two days say the same thing: RefMods beat everything else for keeping a character consistent in MiniMax H3, and they take seconds instead of a training run. Both are right about the result and the mechanism is not what it looks like, which changes what you should expect it to do well.
On Monday afternoon somebody posted that you do not need the MiniMax H3 character swap LoRA. Thirteen hours later somebody posted that you do. Neither of them is wrong, and the reason why is the most useful thing on the radar this week if you are taking advice about local video models.
A 31-second photoreal film of a consistent AI presenter, made on one RTX 5090 with no cuts: reference pictures given jobs, a locked voice track, three cheap seed previews then one upscaled finish, each clip extending the last. The five ways it broke, the picture that fixed each one, the plate rules, the LoRA retrain, and the bill.
Somebody asked today how you count the real cost of AI video once the failed generations are included. We published a 16 minute episode this morning, we keep every take we render, so here are our actual numbers: what we made, what we used, what the retries cost, and the line item nobody prices.
Turn a photograph into an anime character, put that character in six worlds, and make a short film with no dialogue. All of it local, in ComfyUI, on one gaming card. Five things went wrong on the way and all five had the same fix.
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.
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.
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.
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.
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.