Postconceptlab

i think i have missed something help needed python3 server.py Loading Model... {'trained_betas'} was not found in config. Values will be initialized to default values. ftfy or spacy is not...

i have create a 256X256 image

same error i guess

hello i have the same error on a 6 GB 3060 laptop graphic card , so i saw that should be fixed in stable diffusion by using this command PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.6,max_split_size_mb:128...

can you explain to me what to do ?please ?

does it come from th e model ?

i try something elese recreate a conda env on python 3.10.6 its quite long to run the setup.py

RuntimeError: CUDA out of memory. Tried to allocate 26.00 MiB (GPU 0; 5.81 GiB total capacity; 4.54 GiB already allocated; 8.75 MiB free; 4.65 GiB reserved in total by PyTorch)...

i have fixed part of this problem by changing in run.py where the model is load by changing CUDA to CPU , other i have change 3D to 2D in...

i think there is something i can do in the .txt runsetting template is there a way to render only frame by frame what is the parameter