<div data-youtube-video><iframe src="https://www.youtube.com/embed/H5L5sO7dRu8" width="640" height="360" allowfullscreen="true"></iframe></div>
https://youtu.be/H5L5sO7dRu8 
 
Creator: AI-KSK · Collection: Video 327 / six-workflow MiniMax H3 RefMod episode 
 
Workflow file: <code>04_武道馆场景RefMod_双视角批量.json</code> · Cover file: <code>暖光武道馆双视角参考-4.png</code> 
 
<h3>Main features:</h3> 
 
This workflow makes a reusable scene reference from two images of the same location. The example location is a warm, wood-built martial arts dojo, with lanterns, lattice windows, architectural beams, weapon racks and a ceremonial drum. The aim is to preserve a recognizable set across multiple shots while changing action and performers—not to reconstruct a physically exact 3D room. 
 
Unlike the motion graph, the two-reference configuration really is connected: two <code>LoadImage</code> nodes feed <code>refs_image.ref_image_0</code> and <code>refs_image.ref_image_1</code> of <code>MiniMaxH3RefModExtract</code>, then <code>MiniMaxH3RefModInspect</code> provides preview. The two serialized JPEG filenames start <code>Gemini_Generated_Image_...</code>; neither original JPEG is included here. 
 
<h3>Exact values from this JSON</h3> 
 
- <code>name=Dojo_OneLocation</code>, <code>mode=Full Reference</code>, <code>concept_type=background</code>. 
- <code>ref_resolution=1024</code>, <code>pool_h=16</code>, <code>pool_w=16</code>, <code>latent_frames=16</code>. 
- <code>motion_only=false</code>, <code>save=true</code>, <code>subfolder=scene</code>. 
- The text description requests one empty dojo, persistent architectural details and consistent warm light. 
 
<h3>Suggested workflow:</h3> 
 
Supply your own two scene views. Use photographs or renders you have permission to use; ensure both represent one recognizable room. Update both <code>LoadImage</code> selections and, if necessary, rewrite the description so it accurately matches the new environment. Run the graph, inspect the created <code>scene/Dojo_OneLocation</code> reference and load it in the generation workflows. The scene cover shown with this project is not a substitute for the two missing JPEG inputs. 
 
<h3>Limits</h3> 
 
Two-view reference conditioning can encourage visual continuity, but does not provide camera-calibrated geometry, guaranteed room consistency or a digital twin. The golden dojo and split-angle panels on the cover are promotional design. 
 
<h3>Dependencies, tutorial and deployment</h3> 
 
This project uses ComfyUI, MiniMax H3 weights and the <a href="https://github.com/Luisacaotica/ComfyUI-MiniMaxH3Mod" rel="ugc">upstream RefMod node pack</a>; workflows involving <code>VHS_</code> nodes require <a href="https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite" rel="ugc">Video Helper Suite</a>. See <a href="https://huggingface.co/Comfy-Org/MiniMax-H3" rel="ugc">Comfy-Org's H3 model inventory</a> for official distribution guidance. The exact int8-convrot video VAE and Turbo 4-step LoRA named in the creator's JSON need separate availability/provenance checks. We distribute this workflow JSON and its original cover, not external checkpoints or third-party media. Respect applicable rights and licenses. 
 
<a href="https://www.compshare.cn/images/323moGjpvfeM?referral_code=A7fTQUYY9lCDFJwA6MMvoq" rel="ugc">Deploy AI-KSK's H3｜RefMod免训练超级参考 image on 优云智算</a>. Referral disclosure: the deployment link includes an AI-KSK referral code and may support the creator. Check the cloud provider's actual billing and environment before deploying. 
 
<a href="https://youtu.be/H5L5sO7dRu8" rel="ugc">Watch the complete six-workflow YouTube tutorial</a>. This project is one module in that episode. Description and settings were prepared by inspecting the source JSON and transcript, not from a new measured benchmark. 
 
Bilibili tutorial: https://www.bilibili.com/video/BV1F2nZ6SEA7/

MiniMax H3 RefMod Two-View Scene

<div data-youtube-video></div>
https://youtu.be/H5L5sO7dRu8 
 
Creator: AI-KSK · Collection: Video 327 / six-workflow MiniMax H3 RefMod episode 
 
Workflow file: <code>04_武道馆场景RefMod_双视角批量.json</code> · Cover file: <code>暖光武道馆双视角参考-4.png</code> 
 
Main features: 
 
This workflow makes a reusable scene reference from two images of the same location. The example location is a warm, wood-built martial arts dojo, with lanterns, lattice windows, architectural beams, weapon racks and a ceremonial drum. The aim is to preserve a recognizable set across multiple shots while changing action and performers—not to reconstruct a physically exact 3D room. 
 
Unlike the motion graph, the two-reference configuration really is connected: two <code>LoadImage</code> nodes feed <code>refs_image.ref_image_0</code> and <code>refs_image.ref_image_1</code> of <code>MiniMaxH3RefModExtract</code>, then <code>MiniMaxH3RefModInspect</code> provides preview. The two serialized JPEG filenames start <code>Gemini_Generated_Image_...</code>; neither original JPEG is included here. 
 
Exact values from this JSON 
 
- <code>name=Dojo_OneLocation</code>, <code>mode=Full Reference</code>, <code>concept_type=background</code>. 
- <code>ref_resolution=1024</code>, <code>pool_h=16</code>, <code>pool_w=16</code>, <code>latent_frames=16</code>. 
- <code>motion_only=false</code>, <code>save=true</code>, <code>subfolder=scene</code>. 
- The text description requests one empty dojo, persistent architectural details and consistent warm light. 
 
Suggested workflow: 
 
Supply your own two scene views. Use photographs or renders you have permission to use; ensure both represent one recognizable room. Update both <code>LoadImage</code> selections and, if necessary, rewrite the description so it accurately matches the new environment. Run the graph, inspect the created <code>scene/Dojo_OneLocation</code> reference and load it in the generation workflows. The scene cover shown with this project is not a substitute for the two missing JPEG inputs. 
 
Limits 
 
Two-view reference conditioning can encourage visual continuity, but does not provide camera-calibrated geometry, guaranteed room consistency or a digital twin. The golden dojo and split-angle panels on the cover are promotional design. 
 
Dependencies, tutorial and deployment 
 
This project uses ComfyUI, MiniMax H3 weights and the <a href="https://github.com/Luisacaotica/ComfyUI-MiniMaxH3Mod" rel="ugc">upstream RefMod node pack</a>; workflows involving <code>VHS_</code> nodes require <a href="https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite" rel="ugc">Video Helper Suite</a>. See <a href="https://huggingface.co/Comfy-Org/MiniMax-H3" rel="ugc">Comfy-Org's H3 model inventory</a> for official distribution guidance. The exact int8-convrot video VAE and Turbo 4-step LoRA named in the creator's JSON need separate availability/provenance checks. We distribute this workflow JSON and its original cover, not external checkpoints or third-party media. Respect applicable rights and licenses. 
 
<a href="https://www.compshare.cn/images/323moGjpvfeM?referral_code=A7fTQUYY9lCDFJwA6MMvoq" rel="ugc">Deploy AI-KSK's H3｜RefMod免训练超级参考 image on 优云智算</a>. Referral disclosure: the deployment link includes an AI-KSK referral code and may support the creator. Check the cloud provider's actual billing and environment before deploying. 
 
<a href="https://youtu.be/H5L5sO7dRu8" rel="ugc">Watch the complete six-workflow YouTube tutorial</a>. This project is one module in that episode. Description and settings were prepared by inspecting the source JSON and transcript, not from a new measured benchmark. 
 
Bilibili tutorial: https://www.bilibili.com/video/BV1F2nZ6SEA7/

Files with SHA256: 151188f743dbbcffa475a25cfa37a001d1ad6efef20315d254860b4865b24bd8