frank-xwang / InstanceDiffusion

[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"
https://people.eecs.berkeley.edu/~xdwang/projects/InstDiff/
Apache License 2.0
502 stars 29 forks source link

ldm.module has no attribute PositionNet #12

Closed whosthemaan closed 8 months ago

whosthemaan commented 8 months ago

Hi, I am getting the following error after I have all the required libraries set up using the given requirements.txt with conda environment.

image

Thanks

frank-xwang commented 8 months ago

Hi, did you follow our instructions on mode inference? You can run the model inference following this code:

python inference.py \
  --num_images 8 \
  --output OUTPUT/  \
  --input_json demos/demo_cat_dog_robin.json \
  --ckpt pretrained/instancediffusion_sd15.pth \ 
  --test_config configs/test_box.yaml \ 
  --guidance_scale 5 \ 
  --alpha 0.8 \ 
  --seed 0 \ 
  --mis 0.36 \ 
  --cascade_strength 0.3 \

I just tried it locally, it worked fine. Let me know if it does not work for you.

whosthemaan commented 8 months ago

Thanks! It works by using the full command. I was earlier using just the command 'python3 inference.py' with default parameters which seemed to have some issues.