magic-animate
magic-animate copied to clipboard
magic-research
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
It worked 1 time but now it doesn't work. I have 16gb of vram 100%|███████████████████████████████████████████████████████████████████████████████████| 25/25 [08:31
Dear magic-animate Team, I am experiencing difficulties while setting up the magic-animate environment. Here are the specific challenges: 1. Conda Environment Setup Issues: While creating the environment with environment.yaml, I...
I created DensePose videos with Detectron2 and vid2Densepose. The videos I made are 512x512 and about 4 seconds long, just like the DensePose videos provided in the repo. However, the...
Dear MagicAnimate Contributors, I hope this message finds you well. I am reaching out to inquire about the specific input materials required for generating animations using the MagicAnimate tool. While...
mutliple files not available in requirements.txt from nvidia. "ERROR: Could not find a version that satisfies the requirement nvidia-nccl-cu11==2.14.3 (from versions: 0.0.1.dev5) ERROR: No matching distribution found for nvidia-nccl-cu11==2.14.3" "ERROR:...
Hi there I am getting torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 144.00 MiB (GPU 0; 7.77 GiB total capacity; 6.83 GiB already allocated; 46.81 MiB free; 7.17 GiB...
How do i adjust the Sampling Step and Guidance scale to improve the result? Heres what i got but its looks a bit weird 
I have something confused during inference, since I am new in AIGC. I truly believe i have change the "pretrained_model_path" in file animation.yaml to my model path. And i have...
Adding a note in the readme to explain how to get motion paths from a video through a hosted solution.
Metadata
Owner
Metadata
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model