AI-KSK ComfyUI workflow: Video Depth Extractor VDA + DepthCrafter.
This workflow is the dual-route video depth extractor: it takes any source video and outputs a depth-map video, with two interchangeable routes in the same graph - Video Depth Anything (VDA) and DepthCrafter. It is a pure extraction pipeline with no generative model, so it runs fast and the output is a clean monochrome depth sequence you can feed into any depth-guided generation workflow.
Main features:
- Dual depth-extraction routes in one graph: Video Depth Anything (VDA) and DepthCrafter
- No generative model: pure monocular depth estimation, low VRAM footprint
- Input video is resized to about 1MP with lanczos before estimation
- Depth map exported as MP4 via VHS video combine, ready to use as a control signal
Suggested workflow:
Use this workflow to prepare depth control videos for structure-transfer tasks. Pick VDA for general scenes and switch to the DepthCrafter route when you need its motion-preserved depth behavior. Keep the source video steady and well-lit: depth estimation quality follows the source footage, and flickering input produces flickering depth.
RunningHub workflow (try online, no install needed):
https://www.runninghub.ai/zh-cn/post/2103499769275752450?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/BV1pPhU6XERp/
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
Description
AI-KSK ComfyUI workflow: Video Depth Extractor VDA + DepthCrafter.
This workflow is the dual-route video depth extractor: it takes any source video and outputs a depth-map video, with two interchangeable routes in the same graph - Video Depth Anything (VDA) and DepthCrafter. It is a pure extraction pipeline with no generative model, so it runs fast and the output is a clean monochrome depth sequence you can feed into any depth-guided generation workflow.
Main features:
- Dual depth-extraction routes in one graph: Video Depth Anything (VDA) and DepthCrafter
- No generative model: pure monocular depth estimation, low VRAM footprint
- Input video is resized to about 1MP with lanczos before estimation
- Depth map exported as MP4 via VHS video combine, ready to use as a control signal
Suggested workflow:
Use this workflow to prepare depth control videos for structure-transfer tasks. Pick VDA for general scenes and switch to the DepthCrafter route when you need its motion-preserved depth behavior. Keep the source video steady and well-lit: depth estimation quality follows the source footage, and flickering input produces flickering depth.
RunningHub workflow (try online, no install needed):
https://www.runninghub.ai/zh-cn/post/2103499769275752450?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/BV1pPhU6XERp/
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
comfyui
workflow
depth map
workflows
runninghub
video processing
ai-ksk
depth extraction
control signal
depthcrafter
video depth anything
vda
Details
Downloads
27
Platform
CivitAI
Platform Status
Available
Created
9/27/2026
Updated
9/29/2026
Deleted
-