Cheng Lu

DDIM is different from DDPM, and their generation performance are not the same, even for very large steps.

+1

Also, could you please clarify the python version?

@Ir1d I just use the official command in the repo of torch-fidelity.

> +1 Observed the same issue when using it, kind of pity because the main advantage with DPM solver is the low steps required for a good image. Just to...

An example of the stabilizing trick: https://github.com/LuChengTHU/dpm-solver/blob/414c74f62fb189723461aadc91dc6527301e1dbe/dpm_solver_pytorch.py#L1094-L1098

Hi, I'm the first author of DPM-Solver and DPM-Solver++. Our work can greatly accelerate the sampling of stable-diffusion (in only 10-20 steps); here is our newest repo: https://github.com/LuChengTHU/dpm-solver If you...

Here is an example code for applying DPM-Solver++ with cosine beta schedule: https://github.com/LuChengTHU/dpm-solver/blob/5c6ee9f1e6b60c8c54f955fbaab0a6717fc2b75b/examples/ddpm_and_guided-diffusion/sample.sh#L22-L33 The model is the original [improved-ddpm](https://github.com/openai/improved-diffusion), which is the work that firstly introduces the cosine beta schedule.

Here are some example images with "sde-dpmsolver++" in stage-1, and "dpmsolver++" in stage-2 and stage-3: https://github.com/huggingface/diffusers/pull/3344

Emmm, I don't know what happened with the tests...