Downloads · 30 days
0
ComfyUI_workflow_toybox
grmchn/ComfyUI_workflow_toybox
ComfyUI_workflow_toybox is a machine learning model from grmchn. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Personal collection of ComfyUI workflows, experiments, example inputs, and generated previews. This repository is a toybox for multiple ComfyUI setups, not a single model or a single workflow family.
Access
Public
Updated Aug 6, 2026
Repo size
18.8 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.mp413.3 MB · 69%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 7, 2026
- Updated
- Aug 6, 2026
- SHA
- 0830dda5
Model card
From the Hugging Face model README
ComfyUI Workflow Toybox
Personal collection of ComfyUI workflows, experiments, example inputs, and generated previews. This repository is a toybox for multiple ComfyUI setups, not a single model or a single workflow family.
Workflow Sets
| Directory | Contents |
|---|---|
LTX-2.3/ | LTX-2.3 workflow experiments and sample media. |
MiniMax_H3/ | MiniMax H3 reference-to-video pose-transfer workflow and sample inputs. |
genai-expo_vol5/ | Workflows used for an exhibit at 生成AIなんでも展示会 Vol.5, a generative AI exhibition event held on 2026-05-06. |
LTX-2.3
LTX-2.3 workflow experiments.
LTX-2.3-I2V_Audio_Sync.json
An image-to-video workflow with audio sync. It makes a source image sing to the provided audio track.
Workflow download: LTX-2.3-I2V_Audio_Sync.json
Environment note:
Tested on WSL with an RTX 3090. If you are using native Windows, you may need to
change file path separators in load nodes from / to \.
Input image:
<img src="LTX-2.3/dim_sum_sing1024.png" width="400" alt="Input image">Input audio:
<audio controls src="https://huggingface.co/grmchn/ComfyUI_workflow_toybox/resolve/main/LTX-2.3/Chinari-La_14s.mp3"></audio>
Output video:
<video controls src="https://huggingface.co/grmchn/ComfyUI_workflow_toybox/resolve/main/LTX-2.3/LTX-2_3_00005-audio.mp4" width="400"></video>
MiniMax H3
Reference-to-video pose transfer using a character image and a motion reference video. The workflow generates a new video with the character following the reference choreography.
Workflow download: MiniMax_H3_r2v_pose_transfer.json
Input image:
<img src="MiniMax_H3/usamiku1024.png" width="400" alt="Character reference image">Motion reference:
<video controls src="https://huggingface.co/grmchn/ComfyUI_workflow_toybox/resolve/main/MiniMax_H3/jump_happy_sample-girl.mp4" width="400"></video>
GenAI Expo Vol.5
Workflows and sample media used for an exhibit at 生成AIなんでも展示会 Vol.5.
Wan_SCAIL_pose_control(exhibition_vol5_mascot_pose_detect).json: Wan/SCAIL pose-control workflow.LTX-2.3_extend_loop(exhibision_vol5) MultiGPU.json: LTX-2.3 loop extension workflow for a multi-GPU setup.usamiku1024.png,dj_rabbit_2.jpg,syouryuuken2_sample_girl.mp4,bpm140s.wav: sample inputs used with the workflows.
Repository Layout
LTX-2.3/: LTX-2.3 workflows and sample media.MiniMax_H3/: MiniMax H3 pose-transfer workflow and sample inputs.genai-expo_vol5/: GenAI Expo Vol.5 exhibit workflows and sample media.
References
- License
- mit
- Created
- Mar 7, 2026
- Updated
- Aug 6, 2026