Original paper can be found [here](https://arxiv.org/abs/2011.13456).
...
...
@@ -99,7 +99,9 @@ Original paper can be found [here](https://arxiv.org/abs/2011.13456).
Original implementation can be found [here](https://github.com/crowsonkb/v-diffusion-pytorch/blob/987f8985e38208345c1959b0ea767a625831cc9b/diffusion/sampling.py#L296).
- Models: Neural network that models $p_\theta(\mathbf{x}_{t-1}|\mathbf{x}_t)$ (see image below) and is trained end-to-end to denoise a noisy input to an image. Examples: UNet, Conditioned UNet, 3D UNet, Transformer UNet
## API
TODO(Suraj, Patrick)
## Examples
TODO(Suraj, Patrick)
For more detail on the models, please refer to the [docs](https://huggingface.co/docs/diffusers/api/models).
| [stochastic_karras_ve](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stochastic_karras_ve) | [**Elucidating the Design Space of Diffusion-Based Generative Models**](https://arxiv.org/abs/2206.00364) | *Unconditional Image Generation* |
**Note**: Pipelines are simple examples of how to play around with the diffusion systems as described in the corresponding papers.
However, most of them can be adapted to use different scheduler components or even different model components. Some pipeline examples are shown in the [Examples](#examples) below.
- Schedulers are the algorithms to use diffusion models in inference as well as for training. They include the noise schedules and define algorithm-specific diffusion steps.
- Schedulers can be used interchangeable between diffusion models in inference to find the preferred trade-off between speed and generation quality.
- Schedulers are available in PyTorch and Jax.
## API
- Schedulers should provide one or more `def step(...)` functions that should be called iteratively to unroll the diffusion loop during
the forward pass.
- Schedulers should be framework specific.
## Examples
- The DDPM scheduler was proposed in [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) and can be found in [scheduling_ddpm.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddpm.py). An example of how to use this scheduler can be found in [pipeline_ddpm.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/ddpm/pipeline_ddpm.py).
- The DDIM scheduler was proposed in [Denoising Diffusion Implicit Models](https://arxiv.org/abs/2010.02502) and can be found in [scheduling_ddim.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddim.py). An example of how to use this scheduler can be found in [pipeline_ddim.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/ddim/pipeline_ddim.py).
- The PNDM scheduler was proposed in [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://arxiv.org/abs/2202.09778) and can be found in [scheduling_pndm.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_pndm.py). An example of how to use this scheduler can be found in [pipeline_pndm.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pndm/pipeline_pndm.py).
For more information on the schedulers, please refer to the [docs](https://huggingface.co/docs/diffusers/api/schedulers).
