<div data-youtube-video="https://youtu.be/WKGrtR3p_0U"><iframe src="https://www.youtube.com/embed/WKGrtR3p_0U" width="853" height="480" allowfullscreen></iframe></div> 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2089986546912030722?inviteCode=rh-v1111
<h2>MiniMax H3 Two-Stage HD Video Repaint</h2>
Purpose: a MiniMax H3 upscale/re-render graph that takes an existing clip, injects its latent as the base, applies a learned 3D latent 2x upscale, rebuilds high-resolution conditioning, runs a short low-noise refinement pass, then re-attaches the original audio. Intended for users who can resolve the named custom nodes and will check the source video and audio routing before queueing.
<h2>Graph</h2>
28 nodes / 45 links / 24 node types / 5 groups, all saved active. Group A: source video input. B: existing model settings. C: source video injection (MiniMaxH3ImageToVideo + H3InjectVideoLatent). D: learned 3D latent 2x upgrade with rebuilt high-res conditioning. E: original audio lock + original sampling parameters + output.
<h2>Saved configuration (as in the JSON)</h2>
<ul>
<li>UNETLoader: <code>minimax_h3_hybrid_fl2va_ref2va_b25-49-int8.safetensors</code> (default weight dtype).</li>
<li>LoraLoaderModelOnly: <code>minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors</code> at strength 1.</li>
<li>CLIPLoader: <code>qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors</code>, type minimax.</li>
<li>VAELoader: video <code>minimax_h3_video_vae_int8_convrot.safetensors</code>, audio <code>minimax_h3_audio_vae_fp32.safetensors</code>.</li>
<li>MinimaxH3LatentUpscalerNode3D: <code>minimax_h3_latent_upscaler_3d_fp16.safetensors</code>, scale 2, cuda/fp16.</li>
<li>MiniMaxH3SigmaShift: 12 / 3. KSamplerSelect: euler. BasicScheduler: simple, 4 steps, denoise 0.65. H3SigmaRefiner: extra_steps 1, start_at_sigma 0.7, end 0, cosine.</li>
<li>Source clip: LoadVideoUI saved at start 0 / end 5 s / 24 fps / maintain-aspect-ratio; base latent canvas 1344x768, length 124 frames.</li>
<li>High-res conditioning stage: 1344x768 primitives with width/height supplied through math expressions. Output: VHS_VideoCombine, prefix <code>MH3_Universal_Upscale_FL2VA_</code>, h264 mp4, crf 19, 24 fps, original audio routed through MiniMaxH3NativeAudioLock.</li>
</ul>
<h2>How to use</h2>
Replace the source video and set the crop window. The high-res re-render prompt is explicit about preserving motion, identity, composition and camera movement; that is a prompt instruction, not a guarantee. Keep the distillation-matched sampler settings unless you deliberately retune them. Check the saved 5-second window and frame cap against your own clip before queueing.
<h2>Limits and not-verified items</h2>
No inference was run for this listing: no speed, VRAM, upscale-fidelity or audio-sync result is claimed. The saved filename prefix and group names still say FL2VA, which is a naming leftover, not evidence that the graph is a first/last-frame generator. The embedded VHS preview metadata points at a historical cloud run of the author's; it has no runtime effect and is not a credential. The cover image is a promotional still shipped with the source video, not a frame produced by this graph. Weights and input media are not bundled.
Tutorial: <a href="https://www.youtube.com/watch?v=WKGrtR3p_0U" rel="ugc">YouTube</a> · <a href="https://www.bilibili.com/video/BV1Bw8w6yEko" rel="ugc">Bilibili</a>. The workflows are supplied through AI-KSK; verify workflow, node, model, source-video, image, audio and voice rights separately. No blanket commercial or redistribution license is asserted.

MiniMax H3 Two-Stage HD Video Repaint

<div data-youtube-video="https://youtu.be/WKGrtR3p_0U"></div> 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2089986546912030722?inviteCode=rh-v1111
MiniMax H3 Two-Stage HD Video Repaint
Purpose: a MiniMax H3 upscale/re-render graph that takes an existing clip, injects its latent as the base, applies a learned 3D latent 2x upscale, rebuilds high-resolution conditioning, runs a short low-noise refinement pass, then re-attaches the original audio. Intended for users who can resolve the named custom nodes and will check the source video and audio routing before queueing.
Graph
28 nodes / 45 links / 24 node types / 5 groups, all saved active. Group A: source video input. B: existing model settings. C: source video injection (MiniMaxH3ImageToVideo + H3InjectVideoLatent). D: learned 3D latent 2x upgrade with rebuilt high-res conditioning. E: original audio lock + original sampling parameters + output.
Saved configuration (as in the JSON)
<ul>
<li>UNETLoader: <code>minimax_h3_hybrid_fl2va_ref2va_b25-49-int8.safetensors</code> (default weight dtype).</li>
<li>LoraLoaderModelOnly: <code>minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors</code> at strength 1.</li>
<li>CLIPLoader: <code>qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors</code>, type minimax.</li>
<li>VAELoader: video <code>minimax_h3_video_vae_int8_convrot.safetensors</code>, audio <code>minimax_h3_audio_vae_fp32.safetensors</code>.</li>
<li>MinimaxH3LatentUpscalerNode3D: <code>minimax_h3_latent_upscaler_3d_fp16.safetensors</code>, scale 2, cuda/fp16.</li>
<li>MiniMaxH3SigmaShift: 12 / 3. KSamplerSelect: euler. BasicScheduler: simple, 4 steps, denoise 0.65. H3SigmaRefiner: extra_steps 1, start_at_sigma 0.7, end 0, cosine.</li>
<li>Source clip: LoadVideoUI saved at start 0 / end 5 s / 24 fps / maintain-aspect-ratio; base latent canvas 1344x768, length 124 frames.</li>
<li>High-res conditioning stage: 1344x768 primitives with width/height supplied through math expressions. Output: VHS_VideoCombine, prefix <code>MH3_Universal_Upscale_FL2VA_</code>, h264 mp4, crf 19, 24 fps, original audio routed through MiniMaxH3NativeAudioLock.</li>
</ul>
How to use
Replace the source video and set the crop window. The high-res re-render prompt is explicit about preserving motion, identity, composition and camera movement; that is a prompt instruction, not a guarantee. Keep the distillation-matched sampler settings unless you deliberately retune them. Check the saved 5-second window and frame cap against your own clip before queueing.
Limits and not-verified items
No inference was run for this listing: no speed, VRAM, upscale-fidelity or audio-sync result is claimed. The saved filename prefix and group names still say FL2VA, which is a naming leftover, not evidence that the graph is a first/last-frame generator. The embedded VHS preview metadata points at a historical cloud run of the author's; it has no runtime effect and is not a credential. The cover image is a promotional still shipped with the source video, not a frame produced by this graph. Weights and input media are not bundled.
Tutorial: <a href="https://www.youtube.com/watch?v=WKGrtR3p_0U" rel="ugc">YouTube</a> · <a href="https://www.bilibili.com/video/BV1Bw8w6yEko" rel="ugc">Bilibili</a>. The workflows are supplied through AI-KSK; verify workflow, node, model, source-video, image, audio and voice rights separately. No blanket commercial or redistribution license is asserted.

minimaxH3TwoStageHD_v10.json

v1.0

<div data-youtube-video="https://youtu.be/WKGrtR3p_0U"><iframe src="https://www.youtube.com/embed/WKGrtR3p_0U" width="853" height="480" allowfullscreen></iframe></div> 
 
AI-KSK ComfyUI workflow: MiniMax H3 2x Video Redraw. 
 
Main features: 
- General-purpose second-stage high-resolution video redraw that preserves motion, identity, composition, and camera movement. 
- MiniMax H3 Hybrid FL2VA/Ref2VA INT8 model, Qwen3VL 32B text encoder, video/audio VAEs, and 2x 3D latent upscaling. 
- Connected 4-step Euler sampling path with 0.65 denoise and the MiniMax H3 FL2V Turbo LoRA. 
 
Suggested workflow: 
1. Import the JSON into ComfyUI and install the model files and custom nodes referenced by the workflow. 
2. Provide the required text, image, video, or reference inputs for the selected workflow path. 
3. Adjust resolution, denoise, frame settings, and prompt controls, then run the connected video output. 
 
RunningHub workflow: 
https://www.runninghub.ai/post/2089986546912030722?inviteCode=rh-v1111 
 
AI-KSK RunningHub workflow hub: 
https://www.runninghub.ai/user-center/1892566146468511746?inviteCode=rh-v1111 
 
Bilibili tutorial: 
https://www.bilibili.com/video/BV1Bw8w6yEko/ 
 
RunningHub registration and AI tools: 
https://www.runninghub.ai/?inviteCode=rh-v1111 
https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111 
https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111 
https://rhtv.runninghub.ai/projects?inviteCode=rh-v1111 
 
Stable global access: 
https://lelians.com/#/register?code=mFIJ5tZn 
 
TokenRhythm AI model credits: 
https://tokenrhythm.studio/i/rf_tr_kM6wekDquDDZQD4PUNmgiuHA 
 
Youyun Cloud GPU: 
https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq 
https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52 
 
RunPod Cloud GPU: 
https://runpod.io/?ref=sxk5n5m7 
 
Support AI-KSK: 
https://ko-fi.com/aiksk

MiniMax H3 2x Video Redraw

<div data-youtube-video="https://youtu.be/WKGrtR3p_0U"></div> 
 
AI-KSK ComfyUI workflow: MiniMax H3 2x Video Redraw. 
 
Main features: 
- General-purpose second-stage high-resolution video redraw that preserves motion, identity, composition, and camera movement. 
- MiniMax H3 Hybrid FL2VA/Ref2VA INT8 model, Qwen3VL 32B text encoder, video/audio VAEs, and 2x 3D latent upscaling. 
- Connected 4-step Euler sampling path with 0.65 denoise and the MiniMax H3 FL2V Turbo LoRA. 
 
Suggested workflow: 
1. Import the JSON into ComfyUI and install the model files and custom nodes referenced by the workflow. 
2. Provide the required text, image, video, or reference inputs for the selected workflow path. 
3. Adjust resolution, denoise, frame settings, and prompt controls, then run the connected video output. 
 
RunningHub workflow: 
https://www.runninghub.ai/post/2089986546912030722?inviteCode=rh-v1111 
 
AI-KSK RunningHub workflow hub: 
https://www.runninghub.ai/user-center/1892566146468511746?inviteCode=rh-v1111 
 
Bilibili tutorial: 
https://www.bilibili.com/video/BV1Bw8w6yEko/ 
 
RunningHub registration and AI tools: 
https://www.runninghub.ai/?inviteCode=rh-v1111 
https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111 
https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111 
https://rhtv.runninghub.ai/projects?inviteCode=rh-v1111 
 
Stable global access: 
https://lelians.com/#/register?code=mFIJ5tZn 
 
TokenRhythm AI model credits: 
https://tokenrhythm.studio/i/rf_tr_kM6wekDquDDZQD4PUNmgiuHA 
 
Youyun Cloud GPU: 
https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq 
https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52 
 
RunPod Cloud GPU: 
https://runpod.io/?ref=sxk5n5m7 
 
Support AI-KSK: 
https://ko-fi.com/aiksk

Files with SHA256: 40194fc4a1b8378301e38940b3e6b02d7fbf2557243b8f9a72a321224e6dfaae