Add the newest DPM-Solver

[LuChengTHU]

Thanks for your amazing work and interest in DPM-Solver! We have updated DPM-Solver v2.0, which supports four types of diffusion models: noise prediction model, data prediction model, v-prediction model, and score function.

Moreover, we supported both single-step and multi-step versions and the corresponding algorithms for the exponential integrators for both the noise prediction model and the data prediction model.

I'm glad to help if you want to further support our DPM-Solver in this repo :)

[crowsonkb]

Huh... DPM-Solver++(2S) has nice properties of not breaking at low NFE but I feel it's muddier/a little worse at medium NFE, is there some sort of compromise? Thank you, Katherine Crowson

…

On Wed, Nov 2, 2022 at 2:36 AM Cheng Lu ***@***.***> wrote: Thanks for your amazing work and interest in DPM-Solver! We have updated DPM-Solver v2.0, which supports four types of diffusion models: noise prediction model, data prediction model, v-prediction model, and score function. Moreover, we supported both single-step and multi-step versions and the corresponding algorithms for the exponential integrators for both the noise prediction model and the data prediction model. I'm glad to help if you want to further support our DPM-Solver in this repo :) — Reply to this email directly, view it on GitHub <#40>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABDQ67QI4BZGU4OQLETWHL3WGIYYFANCNFSM6AAAAAARU37KQM> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[LuChengTHU]

Hi @crowsonkb

I suggest using the multistep version DPM-Solver++ for guided sampling. e.g., All my experiments for accelerating stable-diffusion use the DPM-Solver++(2M). Please check this page: https://github.com/LuChengTHU/dpm-solver/tree/main/example_v2/stable-diffusion

I also implement a third-order multistep version in https://github.com/LuChengTHU/dpm-solver and huggingface/diffusers#1132 . The third-order solver can further accelerate the results for medium and large NFEs.

If you want to support these algorithms, I'm happy to help :)

[crowsonkb]

I added 2S and 2M! :)

I tried implementing the 3M variant but it seemed worse/images looked kind of deep fried?

[LuChengTHU]

Hi @crowsonkb

My recent work https://arxiv.org/abs/2211.01095 shows that for guided sampling with large guidance scales, high-order solvers all fail to converge in a small number of steps. So in my experience, I think 3M is preferred for unconditional sampling but is unsuitable for conditional (guided) sampling.

[LuChengTHU]

I added 2S and 2M! :)

I tried implementing the 3M variant but it seemed worse/images looked kind of deep fried?

So quick and nice commit! Thank you for the support! I will close the issue.

[Timothy2046]

I used the latest version of A1111 and K-diffusion, but the WEBUI still no DPM Solver and DPM Solver++ in the Sampling method list, why? what should i do to use DPM Solver