---
license: apache-2.0
library_name: diffusers
pipeline_tag: text-to-image
tags:
  - text-to-image
  - prx
  - pixel-space
  - diffusion
---

# PRXPixel (text-to-image, pixel space)

PRXPixel is a **pixel-space** variant of [PRX](https://huggingface.co/collections/Photoroom/prx-models-68e66254c202ebfab99ad38e):
it denoises raw RGB directly (no VAE), conditions on a **Qwen3-VL** text encoder (rather than T5Gemma),
and feeds the generation resolution into the timestep modulation. The denoiser is a ~7B
`PRXTransformer2DModel` with a bottleneck patch projection and a resolution embedder.

- **Resolution:** 1024
- **Transformer:** ~7B params, `torch.bfloat16`
- **Text encoder:** Qwen3-VL text tower (`Qwen3VLTextModel`)
- **VAE:** none (pixel space)
- **Scheduler:** `FlowMatchEulerDiscreteScheduler`

## Requirements

> [!IMPORTANT]
> `PRXPixelPipeline` is **not yet in a released `diffusers`**. Install `diffusers` from the
> branch that adds it, and use `transformers >= 4.57` (the version that introduced
> `Qwen3VLTextModel`):
>
> ```bash
> pip install "transformers>=4.57"
> pip install "git+https://github.com/huggingface/diffusers.git@prx-pixel-pipeline"
> ```

## Usage

```python
import torch
from diffusers import PRXPixelPipeline

pipe = PRXPixelPipeline.from_pretrained("Photoroom/prxpixel-t2i", torch_dtype=torch.bfloat16)
pipe.to("cuda")

prompt = "A front-facing portrait of a lion in the golden savanna at sunset."
image = pipe(prompt, num_inference_steps=28, guidance_scale=5.0).images[0]
image.save("prxpixel_output.png")
```

## License

Released under the Apache 2.0 license. See `LICENSE` and `NOTICE`.