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

models/minimax/minimax-h3-official-i2v/README.md

@@ -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.

models/minimax/minimax-h3-official-t2v/README.md

@@ -0,0 +1,38 @@
+# MiniMax H3 Official T2V
+
+## Summary
+
+Official `MiniMax H3` text-to-video template from the Comfy workflow templates. Useful for direct prompt-to-video testing without needing an image input.
+
+## 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_t2v.json>
+- Original publisher: `Comfy-Org`
+- Date imported: `2026-08-08`
+
+## Developer notes
+
+- The official card links this directly as one of the three primary workflows (`I2V`, `T2V`, `R2V`).
+- Same model-card storage guidance applies here, including the pruned and scaled diffusion-model variants.
+
+## Our notes
+
+- This is the cleanest MiniMax T2V baseline available from an official source.
+- On a `3070`, this is still a reach, but it is worth keeping as the control case when comparing against the turbo LoRA path.
+
+## Required custom nodes
+
+- current official Comfy support for MiniMax templates
+
+## Notes
+
+- Use this as the baseline when deciding whether the community turbo workflow is actually buying enough speed.

models/minimax/minimax-h3-turbo-lora-community/README.md

@@ -0,0 +1,51 @@
+# MiniMax H3 Turbo LoRA Community Workflow
+
+## Summary
+
+Community `MiniMax H3` turbo LoRA workflow intended to cut step count and generation time dramatically compared with the standard MiniMax path.
+
+## Model Family
+
+- `minimax`
+
+## Status
+
+- `imported-only`
+
+## Source
+
+- Community repo page: <https://huggingface.co/drbaph/MiniMax-H3-Turbo-Lora-ComfyUI>
+- Workflow file: <https://huggingface.co/drbaph/MiniMax-H3-Turbo-Lora-ComfyUI/resolve/main/fl_minimax_h3_turbo_lora_example_workflow.json?download=true>
+- Original LoRA project credited by the maintainer: <https://huggingface.co/larryvrh/MiniMax-H3-Turbo-Lora>
+- Original publisher of compatibility conversion: `drbaph`
+- Date imported: `2026-08-08`
+
+## Developer notes
+
+- The maintainer says this repo contains ComfyUI compatibility conversions of the original Turbo LoRA so it works with the pruned/curve-form MiniMax model in ComfyUI.
+- Recommended checkpoint: `minimax_h3_turbo_v4_step600_ema_pruned_comfyui.safetensors`
+- Recommended settings:
+  - `8` steps
+  - `euler`
+  - `beta`
+  - LoRA strength `1.0`
+  - Video sigma shift `12`
+  - Audio sigma shift `4-6`
+- The repo explicitly positions this as a much lower-step route than standard MiniMax generation.
+
+## Our notes
+
+- This is the most interesting MiniMax import for a `3070` because low-step operation is exactly the kind of optimization you need.
+- Still likely tight, but much more realistic than brute-forcing full standard MiniMax settings.
+- This is the first MiniMax workflow I would actually try for local feasibility after the official baseline is understood.
+
+## Required custom nodes
+
+- MiniMax-compatible Comfy support
+- `ComfyUI-KJNodes`-style preview/attention helpers appear in the graph
+- optional acceleration hooks referenced in the source include SageAttention, Sol Attention, Gradient, and Spectrum
+
+## Notes
+
+- Best MiniMax low-step candidate in the current batch.
+- Strong contender for a future `optimized/text-to-video/` or `optimized/image-to-video/` MiniMax master if it performs well enough on your machine.