AssertionError: currently only supporting "eps" and "x0"

[zhiboniu]

I run the command in the guide as this:

python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt <path/to/768model.ckpt/> --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768  

but got this error: AssertionError: currently only supporting "eps" and "x0"

how can I solve it?

[jhqxxx]

Is there a stable diffusionv1 installation library in your python environment, and the code in that library is referenced at runtime, so an error is reported, try pip uninstall latent-diffusion

[dennyX99]

When we do that, it resulting to "ModuleNotFoundError: No module named 'ldm'"

[jhqxxx]

after uninstall, need reinstall this project, pip install -e .

[IceClear]

I guess the code currently does not support v-sampling: https://github.com/Stability-AI/stablediffusion/blob/main/ldm/models/diffusion/ddpm.py#L920