Import new MiniMax H3 and LTX workflows
This commit is contained in:
Morpheus
@@ -0,0 +1,55 @@
|
|||||||
|
# LTX 2.5 T2V / I2V Audio
|
||||||
|
|
||||||
|
## Summary
|
||||||
|
|
||||||
|
`LTX 2.5` ComfyUI workflow that keeps text-to-video and image-to-video under one simplified control node, with audio support and a two-stage generation/refinement pass.
|
||||||
|
|
||||||
|
## Model Family
|
||||||
|
|
||||||
|
- `ltx`
|
||||||
|
|
||||||
|
## Status
|
||||||
|
|
||||||
|
- `imported-only`
|
||||||
|
|
||||||
|
## Source
|
||||||
|
|
||||||
|
- Workflow repo: <https://huggingface.co/SOLRICKS/ltx-2-5-t2v-i2v-audio-comfyui-workflow>
|
||||||
|
- Workflow file: <https://huggingface.co/SOLRICKS/ltx-2-5-t2v-i2v-audio-comfyui-workflow/resolve/main/LTX-2.5_T2V_I2V_Audio.json?download=true>
|
||||||
|
- Original publisher: `SOLRICKS`
|
||||||
|
- Date imported: `2026-08-12`
|
||||||
|
|
||||||
|
## Developer notes
|
||||||
|
|
||||||
|
- The source README says the workflow:
|
||||||
|
- supports both `T2V` and `I2V`
|
||||||
|
- has audio support
|
||||||
|
- keeps control on a simplified main node
|
||||||
|
- exposes duration, resolution, FPS, seed, prompt enhancement, and related toggles
|
||||||
|
- The source README also says it uses a two-stage generation and refinement setup.
|
||||||
|
- This is `LTX 2.5`, not `LTX 2.3`.
|
||||||
|
|
||||||
|
## Our notes
|
||||||
|
|
||||||
|
- Worth watching because it looks simpler than a lot of LTX graphs and it includes audio in the same flow.
|
||||||
|
- Probably not the first thing to queue on an `RTX 3070 / 8 GB`, but it looks like a practical adjacent option if `LTX 2.3` feels too cramped.
|
||||||
|
- The main value here is simplicity plus the two-stage refinement pass, not raw novelty.
|
||||||
|
|
||||||
|
## Required custom nodes
|
||||||
|
|
||||||
|
- `comfyui-crystools`
|
||||||
|
- `comfyui-kjnodes`
|
||||||
|
- `comfyui-videohelpersuite`
|
||||||
|
- `comfyui-impact-pack`
|
||||||
|
- `comfyui-ollama`
|
||||||
|
- `WhatDreamsCost-ComfyUI`
|
||||||
|
|
||||||
|
## Required model files
|
||||||
|
|
||||||
|
- Not spelled out in the source README.
|
||||||
|
- Expect the standard `LTX 2.5` weight stack, encoders, and VAE components used by the workflow.
|
||||||
|
|
||||||
|
## Notes
|
||||||
|
|
||||||
|
- Best same-day `LTX` workflow hit even though it is `2.5` rather than `2.3`.
|
||||||
|
- Good adjacent import if you want to compare the newer branch against your current `LTX 2.3` baseline.
|
||||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,67 @@
|
|||||||
|
# MiniMax H3 INT8 Reference-to-Video
|
||||||
|
|
||||||
|
## Summary
|
||||||
|
|
||||||
|
`MiniMax H3` reference-to-video workflow with `INT8`, Motion Context, and a dedicated reference LoRA path.
|
||||||
|
|
||||||
|
## Model Family
|
||||||
|
|
||||||
|
- `minimax`
|
||||||
|
|
||||||
|
## Status
|
||||||
|
|
||||||
|
- `imported-only`
|
||||||
|
|
||||||
|
## Source
|
||||||
|
|
||||||
|
- Workflow repo: <https://huggingface.co/javawock7618/comfy-MiniMax-H3-workflows>
|
||||||
|
- Workflow file: <https://huggingface.co/javawock7618/comfy-MiniMax-H3-workflows/resolve/main/MiniMax_int8_R2V-javano2608.13.json?download=true>
|
||||||
|
- Original publisher: `javawock7618`
|
||||||
|
- Date imported: `2026-08-12`
|
||||||
|
|
||||||
|
## Developer notes
|
||||||
|
|
||||||
|
- This is the `R2V` branch from the source pack.
|
||||||
|
- The source README describes it as an `INT8` workflow built around:
|
||||||
|
- `Sage-Attention`
|
||||||
|
- `Spectrum`
|
||||||
|
- `Lightx2v LoRA`
|
||||||
|
- optional `Turbo-LoRA`
|
||||||
|
- `Motion Context`
|
||||||
|
- latent upscaling
|
||||||
|
- The source README says the `R2V` branch expects `minimax_h3_ref_lora_rank_256_bf16.safetensors`.
|
||||||
|
- The pack also ships `FLF` and `TTS` workflows, but this import is the dedicated reference-video graph.
|
||||||
|
|
||||||
|
## Our notes
|
||||||
|
|
||||||
|
- This is the strongest same-day MiniMax H3 workflow hit because it is actually about reference conditioning and consistency, not just another turbo LoRA.
|
||||||
|
- It is still a heavy ask for an `RTX 3070 / 8 GB`, but it is much more likely to teach you something useful than a novelty-only MiniMax drop.
|
||||||
|
- Best MiniMax workflow to test if you want a real comparison point against `LTX 2.3` consistency work.
|
||||||
|
|
||||||
|
## Required custom nodes
|
||||||
|
|
||||||
|
- `ComfyUI-Spectrum-MiniMax-H3`
|
||||||
|
- `ComfyUI-H3-Motion-Context`
|
||||||
|
- `ComfyUI-MiniMaxH3_LatentUpscaler`
|
||||||
|
- `ComfyUI-SolAttn_triton`
|
||||||
|
- `ComfyUI-GGUF` if you swap to GGUF-based variants
|
||||||
|
- `comfyui-easy-use`
|
||||||
|
- `comfyui-kjnodes`
|
||||||
|
- `comfyui-impact-pack`
|
||||||
|
- `comfyui-ollama`
|
||||||
|
- `comfyui-videohelpersuite`
|
||||||
|
- `WhatDreamsCost-ComfyUI`
|
||||||
|
- `comfyui_nvidia_rtx_nodes`
|
||||||
|
- `was-node-suite-comfyui`
|
||||||
|
|
||||||
|
## Required model files
|
||||||
|
|
||||||
|
- `Comfy-Org/MiniMax-H3`
|
||||||
|
- `minimax_h3_ref_lora_rank_256_bf16.safetensors` from `Kijai/MiniMax-H3-experimental`
|
||||||
|
- optional `Kijai/MiniMax-H3_comfy`
|
||||||
|
- optional `drbaph/MiniMax-H3-Turbo-Lora-ComfyUI`
|
||||||
|
|
||||||
|
## Notes
|
||||||
|
|
||||||
|
- This is the best current MiniMax reference-video import in the repo.
|
||||||
|
- If your goal is faster low-step novelty renders, the turbo paths are easier to demo, but this one is the better consistency-oriented test.
|
||||||
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user