<div data-youtube-video="https://youtu.be/RhszI-72alU"><iframe src="https://www.youtube.com/embed/RhszI-72alU" width="853" height="480" allowfullscreen></iframe></div> 
 
This R2V workflow combines a character image, a scene image, and a motion video. It is designed for preserving the appearance of the person or character while transferring the movement pattern, stance changes, and performance rhythm from the video reference. 
 
The workflow uses the MiniMax H3 local ComfyUI graph with the connected model, VAE, encoder, sampler, resolution, and video output chain shown in the JSON. 
 
Main features: 
 
- MiniMax H3 FL2VA diffusion model with video VAE and Qwen3-VL text encoding 
- MiniMaxH3ReferenceToVideo route for character, scene, and motion references 
- Character identity and scene composition can be described separately 
- Motion reference controls steps, body alignment, gestures, and performance rhythm 
- Connected 9:16 portrait widescreen resolution at the 0.4 megapixel setting 
- 20-step simple scheduler with res_multistep sampling 
- SaveVideo output for mobile and vertical video workflows 
 
Suggested workflow: 
 
Use the character image for identity, the scene image for environment, and the video only for motion. Keep those roles explicit in the prompt. Begin with a simple movement pattern, verify identity stability, then add more complex gestures or camera changes. 
 
⚡ RunningHub Workflow 
 
Try the workflow online right now - no installation required. 
👉 Workflow: https://www.runninghub.ai/post/2084850873976578049?inviteCode=rh-v1111 
 
If the results meet your expectations, you can later deploy it locally for customization. 
 
🎁 Fan Benefits: Register to get 1000 points + daily login 100 points - enjoy 4090 performance and 48 GB super power! 
 
📵 Bilibili Updates (Mainland China &amp; Asia-Pacific) 
 
If you're in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown. 
📵 Bilibili Video: https://www.bilibili.com/video/BV1MrMk69Ejk/ 
 
☕ Support Me on Ko-fi 
 
If you find my content helpful and want to support future creations, you can buy me a coffee. 
Every bit of support helps me keep creating. 
👉 Ko-fi: https://ko-fi.com/aiksk 
 
📬 Business Contact 
 
For collaboration or inquiries, please contact aiksk95 on WeChat. 
 
⚡ 打开下方链接即可在线体验，无需安装。 
👉 工作流：https://www.runninghub.ai/post/2084850873976578049?inviteCode=rh-v1111 
 
如果你觉得效果理想，也可以在本地进行自定义部署。 
 
🎁 粉丝福利：注册即可领取 1000 积分，每日登录再领 100 积分，体验 4090 与 48 GB 超大显存性能。 
 
📵 B站视频（中国大陆及亚洲地区） 
 
如果你在中国大陆或亚洲地区，可以通过下面的视频查看工作流的实测效果与创作思路。 
📵 B站视频：https://www.bilibili.com/video/BV1MrMk69Ejk/ 
 
我会在夸克网盘持续更新模型资源： 
👉 https://pan.quark.cn/s/07bdc81784ce

MiniMax H3 Character-Motion R2V

<div data-youtube-video="https://youtu.be/RhszI-72alU"></div> 
 
This R2V workflow combines a character image, a scene image, and a motion video. It is designed for preserving the appearance of the person or character while transferring the movement pattern, stance changes, and performance rhythm from the video reference. 
 
The workflow uses the MiniMax H3 local ComfyUI graph with the connected model, VAE, encoder, sampler, resolution, and video output chain shown in the JSON. 
 
Main features: 
 
- MiniMax H3 FL2VA diffusion model with video VAE and Qwen3-VL text encoding 
- MiniMaxH3ReferenceToVideo route for character, scene, and motion references 
- Character identity and scene composition can be described separately 
- Motion reference controls steps, body alignment, gestures, and performance rhythm 
- Connected 9:16 portrait widescreen resolution at the 0.4 megapixel setting 
- 20-step simple scheduler with res_multistep sampling 
- SaveVideo output for mobile and vertical video workflows 
 
Suggested workflow: 
 
Use the character image for identity, the scene image for environment, and the video only for motion. Keep those roles explicit in the prompt. Begin with a simple movement pattern, verify identity stability, then add more complex gestures or camera changes. 
 
⚡ RunningHub Workflow 
 
Try the workflow online right now - no installation required. 
👉 Workflow: https://www.runninghub.ai/post/2084850873976578049?inviteCode=rh-v1111 
 
If the results meet your expectations, you can later deploy it locally for customization. 
 
🎁 Fan Benefits: Register to get 1000 points + daily login 100 points - enjoy 4090 performance and 48 GB super power! 
 
📵 Bilibili Updates (Mainland China &amp; Asia-Pacific) 
 
If you're in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown. 
📵 Bilibili Video: https://www.bilibili.com/video/BV1MrMk69Ejk/ 
 
☕ Support Me on Ko-fi 
 
If you find my content helpful and want to support future creations, you can buy me a coffee. 
Every bit of support helps me keep creating. 
👉 Ko-fi: https://ko-fi.com/aiksk 
 
📬 Business Contact 
 
For collaboration or inquiries, please contact aiksk95 on WeChat. 
 
⚡ 打开下方链接即可在线体验，无需安装。 
👉 工作流：https://www.runninghub.ai/post/2084850873976578049?inviteCode=rh-v1111 
 
如果你觉得效果理想，也可以在本地进行自定义部署。 
 
🎁 粉丝福利：注册即可领取 1000 积分，每日登录再领 100 积分，体验 4090 与 48 GB 超大显存性能。 
 
📵 B站视频（中国大陆及亚洲地区） 
 
如果你在中国大陆或亚洲地区，可以通过下面的视频查看工作流的实测效果与创作思路。 
📵 B站视频：https://www.bilibili.com/video/BV1MrMk69Ejk/ 
 
我会在夸克网盘持续更新模型资源： 
👉 https://pan.quark.cn/s/07bdc81784ce

minimaxH3Character_v10.json

v1.0

<div data-youtube-video="https://youtu.be/RhszI-72alU"><iframe src="https://www.youtube.com/embed/RhszI-72alU" width="853" height="480" allowfullscreen></iframe></div> 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2084850873976578049?inviteCode=rh-v1111
<h2>MiniMax H3 R2V-03 character image + motion video</h2>
A MiniMax H3 omni-modal video graph exported from episode 288. 37 nodes / 46 links. Character LoadImage inputs plus LoadVideo -&gt; Video Slice -&gt; GetVideoComponents for the motion source, and one LoadAudio. 9:16 at 0.4 MP, 4 s.
<h2>Saved configuration</h2>
<ul>
<li>UNETLoader <code>minimax_h3_fl2va_bf16.safetensors</code>; CLIPLoader <code>qwen3vl_32b_minimax_h3_int8_convrot.safetensors</code> (type minimax); VAELoader video <code>minimax_h3_video_vae_fp16.safetensors</code> + audio <code>minimax_h3_audio_vae_fp32.safetensors</code>.</li>
<li>The saved graphs contain no LoRA nodes.</li>
<li>Sampling: <code>KSamplerSelect</code> res_multistep with <code>BasicScheduler</code> simple, 20 steps, denoise 1; <code>SamplerCustomAdvanced</code> for the custom chain.</li>
<li>Conditioning: <code>MiniMaxH3ImageToVideo</code> / <code>MiniMaxH3ReferenceToVideo</code> saved at 1344x768 / 124 / match where present; ResolutionSelector and duration values are quoted per item above; output goes to SaveVideo prefix <code>video/MiniMax_H3</code>.</li>
</ul>
<h2>How to use</h2>
Character stills define identity; the video supplies the motion. The audio path is present; check which branch the saved prompt expects before queueing.
<h2>Limits and not-verified items</h2>
No inference was run for this listing: no speed, VRAM, audio-sync or quality claim is made. Values are quoted from the saved nodes. The graph's notes link the official Comfy-Org/MiniMax-H3 model files and the MiniMax blog; those notes are preserved and this listing does not claim to be the original template author. Weights, encoder and VAEs are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: <a href="https://www.youtube.com/watch?v=RhszI-72alU" rel="ugc">YouTube</a> · <a href="https://www.bilibili.com/video/BV1MrMk69Ejk" rel="ugc">Bilibili</a>. Workflows supplied through AI-KSK; verify workflow, node, model, image/audio and cover rights separately. No blanket commercial or redistribution license is asserted.

R2V-03 Character Image + Motion Video

<div data-youtube-video="https://youtu.be/RhszI-72alU"></div> 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2084850873976578049?inviteCode=rh-v1111
MiniMax H3 R2V-03 character image + motion video
A MiniMax H3 omni-modal video graph exported from episode 288. 37 nodes / 46 links. Character LoadImage inputs plus LoadVideo -&gt; Video Slice -&gt; GetVideoComponents for the motion source, and one LoadAudio. 9:16 at 0.4 MP, 4 s.
Saved configuration
<ul>
<li>UNETLoader <code>minimax_h3_fl2va_bf16.safetensors</code>; CLIPLoader <code>qwen3vl_32b_minimax_h3_int8_convrot.safetensors</code> (type minimax); VAELoader video <code>minimax_h3_video_vae_fp16.safetensors</code> + audio <code>minimax_h3_audio_vae_fp32.safetensors</code>.</li>
<li>The saved graphs contain no LoRA nodes.</li>
<li>Sampling: <code>KSamplerSelect</code> res_multistep with <code>BasicScheduler</code> simple, 20 steps, denoise 1; <code>SamplerCustomAdvanced</code> for the custom chain.</li>
<li>Conditioning: <code>MiniMaxH3ImageToVideo</code> / <code>MiniMaxH3ReferenceToVideo</code> saved at 1344x768 / 124 / match where present; ResolutionSelector and duration values are quoted per item above; output goes to SaveVideo prefix <code>video/MiniMax_H3</code>.</li>
</ul>
How to use
Character stills define identity; the video supplies the motion. The audio path is present; check which branch the saved prompt expects before queueing.
Limits and not-verified items
No inference was run for this listing: no speed, VRAM, audio-sync or quality claim is made. Values are quoted from the saved nodes. The graph's notes link the official Comfy-Org/MiniMax-H3 model files and the MiniMax blog; those notes are preserved and this listing does not claim to be the original template author. Weights, encoder and VAEs are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: <a href="https://www.youtube.com/watch?v=RhszI-72alU" rel="ugc">YouTube</a> · <a href="https://www.bilibili.com/video/BV1MrMk69Ejk" rel="ugc">Bilibili</a>. Workflows supplied through AI-KSK; verify workflow, node, model, image/audio and cover rights separately. No blanket commercial or redistribution license is asserted.

Files with SHA256: d4d1f897a238a658f8951c8160fe8cc8b103148a782003c0b6b581361e41fb38