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.
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.
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.
The complete recipe behind our presenter’s locked identity. Dataset rules, local AI Toolkit vs cloud Civitai training, the strength dials that matter, and the four rules we paid to learn.