---
license: apache-2.0
tags:
- pytorch
- diffusers
- unconditional-image-generation
datasets:
- uoft-cs/cifar10
language:
- en
base_model:
- google/ddpm-cifar10-32
pipeline_tag: unconditional-image-generation
library_name: diffusers
---

# Flow Matching CIFAR-10 Model

A flow matching model for unconditional image generation trained on the CIFAR-10 dataset. This model uses continuous normalizing flows with the FlowMatchEulerDiscreteScheduler for efficient sampling.

## Model Details

- **Architecture**: UNet2DModel with flow matching
- **Dataset**: CIFAR-10 (32x32 RGB images)
- **Scheduler**: FlowMatchEulerDiscreteScheduler
- **Training Steps**: 1000 timesteps
- **Framework**: Diffusers 0.35.0.dev0

## Flow Matching Configuration

The model uses FlowMatchEulerDiscreteScheduler with the following key parameters:
- **Base shift**: 0.5
- **Shift**: 1.0 (exponential time shifting)
- **Base image sequence length**: 256
- **Max image sequence length**: 4096
- **Stochastic sampling**: Disabled for deterministic generation

## Usage

### Basic Generation

```python
from diffusers import DDPMPipeline

# Load the flow matching model
pipeline = DDPMPipeline.from_pretrained("FrankCCCCC/cfm-cifar10-32")

# Generate an image
image = pipeline().images[0]
image.save("generated_cifar10.png")
```

### Custom Inference Steps

```python
from diffusers import DDPMPipeline

pipeline = DDPMPipeline.from_pretrained("FrankCCCCC/cfm-cifar10-32")

# Generate with custom number of inference steps
num_inference_steps: int = 1000
pipeline.scheduler.set_timesteps(num_inference_steps)
image = pipeline().images[0]
image.save("fast_generated_cifar10.png")
```

### Batch Generation

```python
from diffusers import DDPMPipeline

pipeline = DDPMPipeline.from_pretrained("FrankCCCCC/cfm-cifar10-32")

# Generate multiple images at once
images = pipeline(batch_size=4).images
for i, image in enumerate(images):
    image.save(f"generated_cifar10_{i}.png")
```

## Flow Matching vs Standard Diffusion

This model implements flow matching, which offers several advantages over standard diffusion models:
- **Faster sampling**: More efficient ODE solving with fewer steps
- **Better training stability**: Continuous normalizing flows provide smoother optimization
- **Flexible scheduling**: Exponential time shifting for improved sample quality

## Model Architecture

- **UNet**: Standard UNet2DModel for denoising/flow prediction
- **Scheduler**: FlowMatchEulerDiscreteScheduler with exponential time shifting
- **Output**: 32x32 RGB images matching CIFAR-10 distribution

## Requirements

```bash
pip install diffusers torch torchvision
```

## Samples
1. ![sample_1](https://huggingface.co/FrankCCCCC/cfm-cifar10-32/resolve/main/images/sample0.jpg)
2. ![sample_2](https://huggingface.co/FrankCCCCC/cfm-cifar10-32/resolve/main/images/sample1.jpg)
3. ![sample_3](https://huggingface.co/FrankCCCCC/cfm-cifar10-32/resolve/main/images/sample2.jpg)
4. ![sample_4](https://huggingface.co/FrankCCCCC/cfm-cifar10-32/resolve/main/images/sample3.jpg)
5. ![sample_5](https://huggingface.co/FrankCCCCC/cfm-cifar10-32/resolve/main/images/sample4.jpg)

## Citation

If you use this model, please cite the original flow matching and diffusion literature:

```bibtex
@inproceedings{DDPM,
  author = {Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
  booktitle = {Advances in Neural Information Processing Systems},
  title = {Denoising Diffusion Probabilistic Models},
  url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf},
  year = {2020}
}

@inproceedings{FM,
  title={Flow Matching for Generative Modeling},
  author={Yaron Lipman and Ricky T. Q. Chen and Heli Ben-Hamu and Maximilian Nickel and Matthew Le},
  booktitle={The Eleventh International Conference on Learning Representations },
  year={2023},
  url={https://openreview.net/forum?id=PqvMRDCJT9t}
}

```