ComfyUI Workflow (Image to Video)
required Custom Nodes:
Update rgthree (forked): https://github.com/r-vage/rgthree-comfy
fixed the fast bypasser and applied some of the community fixes
the v1 version of the workflow uses the Wan Video Wrapper custom node.
the others are native versions (comfyui nodes)
its able to extend the initial video, by calculating the entered loop value or the max frame_load cap
Description
a workflow that can be used for i2v or t2v with a14b or wan2.1 14b models, i haven't tested with 5b but should work too
it allows to start the initial render with text to video and extend the video with i2v by using the last frame as new ref image. in that case the 2 additional model loader are needed.
2 presets are in the archive
added the create loop that i've found in the darksidewalker workflow, it's kind of working, in the end it looks like a morph but yea.
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.