Bobby
Bobby
@fire717 thanks for your sharing . movenet onnx+TNN+c++(of post data process) is a good idea.I would have a try.
By the way, May you make a branch which put the post data process code into the model It woud be useful for us to compare to the original tflite...
I met the same error. torch==1.9.1 onnx=1.10.2
> http://68.3.132.170:8080/?action=stream > http://129.10.131.166:8080/?action=stream > http://89.39.27.182:8080/?action=stream > http://66.130.223.168:8080/?action=stream > http://98.30.39.160:8080/?action=stream equipment cameras work！
For alpha pose(0.3.0),which based on torch 1.7 or above, does torch version matters?
@ApolloRay Nice, can you share your method with us? And show us the txt2img speed ? Thanks.
@whpwwy can you share the method you used to fix the bug ? I meet the same error. and when i explict set model_id_or_path value as the model's folder. the...
I am working on Have stream support sdxl-1.0-base model. However, error accured. any suggestions? : ../diffusers/loaders/unet.py", line 260, in load_attn_procs attn_processor = getattr(attn_processor, sub_key) File "../site-packages/torch/nn/modules/module.py", line 1695, in __getattr__...
> set PYTHONPATH=. > > that fixes it This work! on linux shell as : export PYTHONPATH=.
> response = requests.post("http://127.0.0.1:8188/prompt", json={"prompt": prompt}) > print(response.status_code, response.text) seems work to me.