RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2098324174329966593?inviteCode=rh-v1111

Bilibili tutorial video: https://www.bilibili.com/video/BV16DYL6FEsh/

# OpenVDN — Endpoint Wiring with Task-Mode Review

## Purpose and preparation

Resolve the exact model and node versions, inspect task/input agreement and choose authorized images before queueing. Treat saved controls as a starting point, not accepted output evidence.

Images 15/56 connect first_frame/last_frame, with FL2VA base but Ref2VA task still selected. Review this mismatch. Only the main chain is enabled; two complete extra examples and saves37/51 are bypassed. Title 960×544/39 frames is stale versus 896×512/124 widgets.

Composer selects OpenVDN/vdn-minimax-h3 and stage_dmd_8nfe, verify_hashes=false, allow_structural_base=true. ExecutionPlan supplies model/sampler/sigmas; no numeric sigma vector is serialized, and reports are unused. JSON hash validation is not model-weight hash verification. DMD8 labels are not observed evaluations.

Selected dimensions are 896×512, length 124, with no external size/time override. Noise 9527 has fixed control. Generated video/audio from AVDecode reach CreateVideo 24fps/8-bit and one active SaveVideo with auto format/codec. No upscale or interpolation tail is supplied in these exports.

At24fps, 124 output frames would be nominally about5.167 seconds, not a measured duration. All enabled soundtracks come from decoded generated audio; source audio inputs are absent and conditioner mux_audio is unused. Prompt soundscapes are instructions, not audible proof. Inspect actual task resolution, images, timing, speech and endpoints in a small authorized-media test.

## Files and selected assets

- [Workflow JSON]()

- [Selected cover]()

- `qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors`

- `minimax_h3_fl2va_int8_convrot.safetensors`

- `minimax_h3_video_vae_int8_convrot.safetensors`

- `minimax_h3_audio_vae_fp32.safetensors`

## Version and rights

New copies retain the original configuration except recorded historical preview cleanup. No task-mode mismatch is silently repaired. This is descriptive local copy, not a published upgrade.

No inference, visual/audio acceptance, hardware timing or license verification was performed. Covers are selected same-stem WebP assets, not accepted output samples. Weights and external input media are not bundled. Check workflow, nodes, models, LoRAs, images and cover permissions separately; no blanket commercial license or speed winner is asserted.

[Source-provided tutorial](https://www.youtube.com/watch?v=g3QmFCf2dF4) · [Source workflow entry](https://www.runninghub.cn/post/2098317979074260993/?inviteCode=rh-v1111)

Links not live-verified. The workflow is supplied through AI-KSK.