Upload 2 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+MiniMax-H3[[:space:]]FL2VA-Curve[[:space:]]Q5_1[[:space:]]-[[:space:]]MinimaxH3.gguf filter=lfs diff=lfs merge=lfs -text

MiniMax-H3 FL2VA-Curve Q5_1 - MinimaxH3.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6110fe6f6992bfb1ec86518aa92a0644fec4facf25e561430aebfc2a5f4a874
+size 15227425440

MiniMax-H3 FL2VA-Curve Q5_1 - MinimaxH3.txt

@@ -0,0 +1,14 @@
+MiniMax-H3 FL2VA-Curve Q5_1 - MinimaxH3
+
+need ComfyUI 0.30.0 or newer
+
+Before you load one of these: ComfyUI-GGUF does not know this architecture out of the box.
+Its loader keeps a hardcoded allow-list, and minimax_h3 is not in it, so you get ValueError: Unexpected architecture type in GGUF file: 'minimax_h3'. Install ComfyUI-H3-Multishot and run python apply_gguf_arch_patch.py from its folder, then restart ComfyUI. It is one line, idempotent, and applies whichever DiT loader you use.
+
+You also need the text encoder (Qwen3-VL GGUF + its mmproj sidecar) and the VAEs. A file here is the transformer and nothing else — on its own it generates nothing. Load the encoder with the pack's H3ClipLoaderAny at type = minimax, not with “CLIPLoader (GGUF)”, which has no minimax type and fails with a confusing tokenizer error instead.
+
+You also need the text encoder
+
+A file here is the transformer and nothing else. The DiT alone generates nothing. Get the Qwen3-VL encoder (Civitai / Hugging Face) and take the mmproj file with it — it is required for image conditioning and for multi-shot chaining, which feeds the previous shot's last frame through the encoder's vision path. VAEs come from Comfy-Org/MiniMax-H3.
+
+The encoder and the DiT together do not fit on a 32 GB card. Evict the encoder once conditioning is computed — the node pack's keyframe and multishot nodes do this for you, and it is worth roughly a 4× difference in render time.