Instructions to use internlm/EndoCoT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use internlm/EndoCoT with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("internlm/EndoCoT", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Something wrong about the test results of VSP.
#2
by carsun00 - opened
Hi! Dear EndoCOT group,when I try to test the VSP, I found that every results seems to finish a TSP mission and they tried to connect every hole, which made me very confused. However , when it comes to 8x8 mission, it works very well and becomes normal again. I doubt that is there any problem with the ckpt? If the answer is yes, I really hope that you can update the ckpt. I really wish to hear from your reply.
