Instructions to use zai-org/CogVideoX1.5-5B-I2V with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zai-org/CogVideoX1.5-5B-I2V with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zai-org/CogVideoX1.5-5B-I2V", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
fp16
#16 opened about 1 year ago
by
tangxiaochu
Add pipeline tag, library name and set inference to true
#15 opened about 1 year ago
by
nielsr
The sample script needs to be updated to fix the OOM (Out of Memory) issue and long inference time caused by not explicitly specifying the height and width.
#14 opened over 1 year ago
by
llmx
CogVideoX1.5-5B-I2V Windows and Cloud Tutorial - 1-Click To Install With all Optimizations on Windows Python 3.11 VENV
#13 opened over 1 year ago
by
MonsterMMORPG
Difference between 1.5 and THUDM/CogVideoX-5b-I2V?
1
#12 opened over 1 year ago
by
askyforever
torch.OutOfMemoryError
1
#10 opened over 1 year ago
by
JohnneyQin
Could you provide the image used for the demo in README?
👀 1
1
#9 opened over 1 year ago
by
limingcv
vram ,multi gpu
1
#8 opened over 1 year ago
by
tangxiaochu
Any optimization ways to accelerate the speed of inference
8
#7 opened over 1 year ago
by
mayukitan