With this workflow you can turn an image into a video.
SVD, AnimateDiff, ReActor and Frame interpolation were used in this workflow.
Links to the models are available in the workflow.
You can skip the second AnimateDiff step if you want.
Description
Full LCM is in use.
Fewer nodes, faster results
FAQ
Comments (11)
How do you use this stuff? I have no idea how to do it.
Can you try this workflow and see if it works? https://we.tl/t-k3tr4zfDec
I changed the file, you can also download and try again
oh sorry no i meant i don't know how to do animated video at all...like i don't understand the processs
@Mr_Unknown this video is similar to my workflow, maybe it will help.
https://www.youtube.com/watch?v=HOVYu2UbgEE&t=560s
Very nice workflow, thanks for sharing ⭐
Thanks a lot! I'm glad you liked it. 🤘
How can I upload this to models lab models?
Hi) Can you tell me how to fix:
Error occurred when executing ImageOnlyCheckpointLoader: ERROR: Could not detect model type of: /workspace/ComfyUI/models/checkpoints/animatelcmSVDXtForOpen_v10.safetensors
File "/workspace/ComfyUI/execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/workspace/ComfyUI/execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/workspace/ComfyUI/execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/workspace/ComfyUI/comfy_extras/nodes_video_model.py", line 21, in load_checkpoint out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=False, output_clipvision=True, embedding_directory=folder_paths.get_folder_paths("embeddings")) File "/workspace/ComfyUI/comfy/sd.py", line 513, in load_checkpoint_guess_config raise RuntimeError("ERROR: Could not detect model type of: {}".format(ckpt_path))
Where to download and put the BLIP caption model? The BLIP loader is not detecting the model I downloaded
I have the same issue. Did you figure this out?