If you need a prompt for the image, run it through JoyCaptions: Joy Caption Alpha Two - a Hugging Face Space by fancyfeast
Uses the T5 encoder, so its recommended to style your prompt as natural language. Eg 'this is a video of a woman taking a walk in a busy hong kong street'. The context length for the T5 is 256 tokens, so making your prompt long will work fine.
The workflow will throw an error if you exceed the token limit. If you get an Exception error , reduce the prompt size!
Link to workflow: Image to Video with CogVideo X | ComfyUI Workflow | Tensor.Art
Animate your images using Cogvideo X GitHub - kijai/ComfyUI-CogVideoXWrapper
PS: Stuff posted to NSFW gallery is for some reason not visible in the gallery below.
Feel free to post NSFW content tho to the other channels in the meantime :)