Add latest MiniMax H3 I2V and R2V workflows

2026-09-03 18:06:39 +00:00
parent d4808b8fc9
commit d5e4a40957
4 changed files with 71 additions and 15 deletions
@@ -0,0 +1,53 @@
+# MiniMax H3 I2V Javawock Pack
+
+## Summary
+
+Same-day `MiniMax H3` first/last-frame image-to-video workflow from the updated `javawock7618` pack. This is the newer I2V graph to keep alongside the older `2608` import.
+
+## Model Family
+
+- `minimax`
+
+## Status
+
+- `imported-only`
+
+## Source
+
+- Workflow pack page: <https://huggingface.co/javawock7618/comfy-MiniMax-H3-workflows>
+- Workflow file: <https://huggingface.co/javawock7618/comfy-MiniMax-H3-workflows/raw/main/MiniMax_int8_I2V-javano2609.1.1.json>
+- Original publisher: `javawock7618`
+- Date imported: `2026-09-03`
+
+## Developer notes
+
+- The source README describes this as the `First-Last-Frame` workflow.
+- It keeps the pack's INT8 / Sol-Attn / SLA-Attention / Spectrum stack and the integrated latent upscaler path.
+- The bundle also adds Fun ControlNet Union support for V2V-style control-video guidance.
+
+## Our notes
+
+- Best new MiniMax H3 I2V import from today if you want the newer pack version.
+- Still a heavy workflow for an `RTX 3070` with `8 GB` VRAM, so this is a test target rather than a casual run.
+- Useful comparison point against the older MiniMax H3 and LTX first-frame graphs already in the repo.
+
+## Required custom nodes
+
+- `ComfyUI-SolAttn_triton`
+- `ComfyUI-Spectrum-MiniMax-H3`
+- `ComfyUI-H3-SLA-Attention`
+- `ComfyUI-H3-FaceRefine`
+- `ComfyUI MiniMax-H3 Latent Upscaler`
+- `ComfyUI-Switchboard`
+
+## Required models
+
+- `Comfy-Org/MiniMax-H3`
+- `Kijai/MiniMax-H3-experimental` for the Fun ControlNet Union path
+- `lightx2v/Minimax-h3-Turbo` if acceleration is enabled
+- `drbaph/MiniMax-H3-Turbo-Lora-ComfyUI` if the optional turbo LoRA path is enabled
+- `LBH-123-AI/Minimax_h3_latent_Upscaler` if latent upscaling is enabled
+
+## Notes
+
+- This is the newer same-day I2V graph from the pack, not just a duplicate label.