Hey guys 👋🏻 Ok so I have been playing with Video Reference in the new Director V2.1 and thought I would share the test node I was using. Take a look at the video below 👇 I would really love to see some examples in the community, so take this as a challenge! The Github repo is below and the link to the workflow is attached. Have fun!! GitHub: https://github.com/muse-collective-26/Muse-Video-Swap-H3

Ok all, I am perfecting my video edit section of the V2.1 Director. Does anyone have a short clip, under 15 seconds (so one chunk), can be there own or some ref they have etc.... Send me the clip with what you want me to change or edit in the video (not a project you want fixing!). Something just for fun. I will select 4 or 5 and make the edits. I want to test this new mode out. Drop your clip and instructions (preferred edit in the comments) 👇👇

Perhaps some of you have also encountered the issue where Minimax fails to follow your prompts. Regardless of which Minimax model I tried, 70% of the time the output didn't match what I had requested—it was driving me absolutely crazy. Yesterday, I stumbled upon a YouTube video by Mickmumpitz, which revealed that the text encoder I had been using (`qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors`) is actually designed exclusively for Nvidia Blackwell-series graphics cards. Since I’m still running an older 3090 24GB card, I decided to switch to a different text encoder (`qwen3vl_32b_minimax_h3_int8_convrot.safetensors`). Since making that change, the results now align with my prompts 90–95% of the time.

I'm having trouble getting my LLM to provide a Json file that Muse Director import will accept. Andy are you able to send me some working Json Import examples so i can provide Claude to look at. I had my HTML ollma prompt generate provide a working json that Muse director accepted. I however made some tweaks that have upset it.😉. Be nice to provide Claude some working examples. THANKS

Hi. I am having an issue with the transcription function. It only works when I keep the duration under 30 seconds. As soon as I try to analyze the entire song, I receive this error message (see attachment). However, according to the console, the transcription is complete: [INFO] [MuseMinimaxDirector] Transcribing E:\AI\ComfyUI-Easy-Install\ComfyUI\input\MuseComboProjects/project_cc564fb98be94347ac2b9e6116877a92/f49488bb3617911a52da.mp3 [0.00s-239.20s] with Whisper 'small' (CPU)... [INFO] HTTP Request: GET https://huggingface.co/api/models/Systran/faster-whisper-small/revision/main "HTTP/1.1 200 OK" [INFO] Processing audio with duration 03:59.200 [INFO] Detected language 'en' with probability 0.87 [INFO] [MuseMinimaxDirector] Transcription complete: 65 segment(s).