I am by no means an expert and would love any feedback or additional thoughts. I have spent a bit of time tinkering with Animate Diff workflows specifically for morphs and transformation GIF's and animations.
Shoutout to a1lazydog for the excellent workflow that set me down this path. (Animatediff Workflow: Openpose Keyframing in ComfyUI - 3 keyframes v1.1 | Stable Diffusion Workflows | Civitai)
I don't use all nodes at all times. Latent upscale really helps smooth motion. Distant faces get warped even with upscale and ReActor seems to make the faces look nice. I think there is some refining to do here!
I am using ControlNet Tile for images. I will use Photoshop to make backgrounds similar between them. I have found that low ControlNet weights give the Txt2Vid room to breathe but often play with the strength weights.
Description
A lot of complexity added. Thanks to QR Code morphing workflow for the base and built from there.
FAQ
Comments (6)
This looks awesome, but Iam having a hard time trying to recreate it. Could you also share all the input images and video file(\right_pan.mp4)to run this as well as tell us where to find "qrCodeMonster_v10.safetensors" and what the QRCode stuff is for?
Reuploaded the Zip file with all the video files I've made. QR Code can be downloaded here. I seem to have good luck with V1 but haven't messed with V2 much: https://civitai.com/models/90940?modelVersionId=96917
It doesn't work
none of the aniamtediff modules work bro dont even bother looking lol
When trying to use the workflow, some nodes flag red due to missing connections. I know you say you don't use all the nodes, but would it be possible for you to add more notes to it so anyone else who does use the workflow knows what to do to adjust?
Have tried getting this to work, had some trouble. Been a while, do you have any updates maybe?