Add low-vram workflow batch for Z-Image, LTX, and MiniMax

2026-08-08 21:54:27 +00:00
parent d87cc7843e
commit 1a42e3579f
15 changed files with 22179 additions and 0 deletions
@@ -0,0 +1,40 @@
+# MiniMax H3 Official I2V
+
+## Summary
+
+Official `MiniMax H3` image-to-video template from the Comfy workflow templates. Good baseline for seeing how the official Comfy packaging expects MiniMax to be wired.
+
+## Model Family
+
+- `minimax`
+
+## Status
+
+- `imported-only`
+
+## Source
+
+- Model card: <https://huggingface.co/Comfy-Org/MiniMax-H3>
+- Workflow file: <https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_minimax_h3_i2v.json>
+- Original publisher: `Comfy-Org`
+- Date imported: `2026-08-08`
+
+## Developer notes
+
+- The model card lists several pruned and scaled model variants, including `pruned_fp8_scaled` files, which are the most interesting ones for tighter hardware.
+- The official card also separates diffusion models, text encoders, and VAEs clearly, which is useful when wiring custom local setups.
+
+## Our notes
+
+- This is the safest MiniMax baseline we have.
+- On a `3070`, MiniMax still looks tight to heavy, but the pruned/fp8-scaled model variants make it worth keeping on the board.
+- If MiniMax becomes practical for you, this official workflow is the best starting point before moving into community turbo variants.
+
+## Required custom nodes
+
+- current official Comfy support for MiniMax templates
+
+## Notes
+
+- Best first official MiniMax import.
+- Most relevant low-VRAM angle is choosing the pruned/fp8-scaled files from the model card rather than the heavier variants.