The first three Making R01 tutorials are live. We’re using our orange robot to work through LoRA Pilot (www.lorapilot.com), from the first session to preparing a dataset. 1. One robot, five worlds A first session in the LoRA Pilot workspace. https://youtu.be/_Z85_IgteLQ 2. Directing the scene Camera prompts in ComfyUI and a look at how closely the results follow them. https://youtu.be/Q3NH6ZSfbOM 3. Preparing the dataset Upload an archive, review the images and edit captions in TagPilot. This episode covers preparation; we don’t run training yet. https://youtu.be/07dfuzvv_Ik

A LoRA and a RefMod can both help with a character, but you get there differently A LoRA learns adapter weights through training. The Full Reference mode in this MiniMax H3 workflow encodes your images into a reusable reference file. No LoRA training run Loose analogy: a LoRA is practice, a RefMod is a reference sheet beside the drawing board. Neither stops the artist from occasionally getting things wrong I made RefMod Pilot to make that second route easier to try. Upload a few consistent photos, save the reference, then use it in a video workflow with Characters → Scene → Output. Scene settings include aspect ratio and duration in seconds. The technical nodes sit inside a subgraph There's a bundled orange robot example made from six views. Its reference took 5.7 seconds to encode on a 48 GB Blackwell MIG instance. That's one encoding measurement, not a video-generation benchmark. More references still add cost when generating, and the robot's finished-video likeness is untested I'm the developer of LoRA Pilot. RefMod Pilot is free to download, but you'll need the H3 models, dependencies and GPU compute. Credit for the underlying reference nodes goes to Luisacaotica GitHub: https://github.com/vavo/minimax-h3-refmod-pilot Hugging Face: https://huggingface.co/no3us/minimax-h3-refmod-pilot

Hi everyone, I’m Michal. I make AI short films and build LoRA Pilot, a free, open-source workspace for dataset preparation, LoRA training, and image/video generation. I joined because the focus here on finished productions is close to what I’m working on. My latest short, The Recast, turns character drift into the plot: a woman in a red jacket is in a dockside chase, but the film keeps recasting her face. The storytelling idea is to keep the jacket, briefcase and action readable while identity becomes the joke. The line is: “Could I finish one scene as me?” It runs one minute, with English captions and AI-generated visuals. https://youtu.be/eh2raYusTMk I’d value specific editing feedback: does the face-change premise make sense before the dialogue explains it? And which cut, if any, loses the chase’s continuity? A timestamp would help. Disclosure: this is my film and a showcase for the open-source tool I develop. Happy to discuss the character-consistency problem with fellow creators.