stablediffusion
stablediffusion copied to clipboard
black images
I down this repo and weight file (https://huggingface.co/stabilityai/stable-diffusion-2-1/blob/main/v2-1_768-ema-pruned.ckpt),and run demo as "python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt v2-1_768-ema-pruned.ckpt --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768 "
run without any error output, but get a black output image
Then i change another weight (https://huggingface.co/stabilityai/stable-diffusion-2-1-base/resolve/main/v2-1_512-ema-pruned.ckpt )
Not black but still nonsence
Any idea to solve this problem? Thanks alot
I had the same issue until I changed this:
--config configs/stable-diffusion/v2-inference-v.yaml
to
--config configs/stable-diffusion/v2-inference.yaml