Stability-AI / stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models
MIT License
38.83k stars 5.01k forks source link

black images #175

Open TengfeiHou opened 1 year ago

TengfeiHou commented 1 year ago

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

grid-0011

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 grid-0010

Any idea to solve this problem? Thanks alot

Bohndiggin commented 1 year ago

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