Instructions to use zai-org/cogvlm2-llama3-caption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zai-org/cogvlm2-llama3-caption with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("zai-org/cogvlm2-llama3-caption", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
中文效果怎么样呢
#1
by loong - opened
中文效果怎么样呢
这是个英语模型哦,CogVideoX也是英语的
where is the explained Video for installation and using with ComfyUI. ThaNK YOU. Btw, can you add motion brushes to the CogvideoX- I2V ComfyUI work flow? It would be perfect.
We released GLM-4V-Plus-0111 beta, which can generate better video captions. Find more here: https://bigmodel.cn/dev/api/normal-model/glm-4v
If you want to generate a Chinese caption, you can give the model a prompt as "请仔细描述这个视频".