Cannot use with Native Comfy Minimax H3 I2V
#29
by Fatcraig - opened
Trying to use one of these quants in the native 'Minimax H3 Image to Video' node throws an error immediately.
The 'qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors' text encoder from the Minimax H3 repo works fine, I have been using it for many generations now.
Anything obvious i'm missing or do I need to use a different CLIP loader, etc? Thanks for any help
