# PRX
PRX is Photoroom's open-source text-to-image model, a 1.3B transformer released as nine checkpoints at 256, 512 and 1024 px. PRX Pixel is a 7B sibling that denoises pixels directly, with no autoencoder. LibreYOLO runs all ten through the LibreGen factory on the diffusers pipelines.
Tasks: Image generation. Install: pip install "libreyolo[gen]".
Verified against LibreYOLO v1.8.0.

## Install

```bash
pip install "libreyolo[gen]"
```

PRX Pixel needs `diffusers>=0.39` and says so when it loads; the extra's
floor is 0.38 so it can sit next to the Marigold extra.

## Generate

Weights download from LibreYOLO's byte-identical mirrors of Photoroom's
repositories on first use.

**Python**

```python
from libreyolo import LibreGen

model = LibreGen("prx-512-sft")
result = model("a red fox sleeping in fresh snow", seed=0)
result.save("fox.png")             # the PNG also stores prompt, seed and params
```

**Settings**

```python
from libreyolo import LibreGen

model = LibreGen("prx-512-sft-distilled")          # 8-step distillation
result = model("a red fox", steps=8, guidance=1.0)

model = LibreGen("prx")                            # prx-1024-beta
result = model("a red fox", negative="blurry", imgsz=1024, seed=0)

model = LibreGen("prxpixel", offload=True)         # prxpixel-7b, needs diffusers>=0.39
results = model(["a red fox", "a blue jay"], n=2, save=True)
```

**CLI**

```bash
libreyolo generate prompt="a red fox" model=prx-512-sft negative="blurry"
libreyolo generate prompt="a red fox" model=prxpixel-7b seed=0 n=4
```

A string is always a prompt. One prompt with `n=1` returns a `Results`; a
list of prompts or `n > 1` returns a flat list, and `stream=True` a
generator. `result.generated` holds the image (`array`, `image`), the
`prompt`, the `seed` that reproduces it and the `params` in effect. Every
family knob is optional; one the family does not have raises and lists the
supported ones. See the [image generation](/docs/tasks/image-generation) task
page for prompts, seeds, devices and offload.

## Variants

| Model | Parameters | Knobs (defaults) | GPU memory (library figure) |
| --- | --- | --- | --- |
| `prx-1024-beta` (alias `prx`) | 1.3B | `steps` (28), `guidance` (5.0), `negative` ("") | about 21 GB |
| `prx-512-sft-distilled` | 1.3B | `steps` (8), `guidance` (1.0), `negative` ("") | about 16 GB |
| `prx-512-sft`, `prx-512` | 1.3B | `steps` (28), `guidance` (5.0), `negative` ("") | about 16 GB |
| `prx-512-dc-ae-sft-distilled` | 1.3B | `steps` (8), `guidance` (1.0), `negative` ("") | about 16 GB |
| `prx-512-dc-ae-sft`, `prx-512-dc-ae` | 1.3B | `steps` (28), `guidance` (5.0), `negative` ("") | about 16 GB |
| `prx-256-sft`, `prx-256` | 1.3B | `steps` (28), `guidance` (5.0), `negative` ("") | about 16 GB |
| `prxpixel-7b` (alias `prxpixel`) | 7B | `steps` (28), `guidance` (5.0), `negative` ("") | about 18 GB |

The number is the native resolution. `-dc-ae` uses the 32x DC-AE
autoencoder instead of the FLUX.1 VAE, so its sides round up to a multiple of
32 instead of 16. `-sft` is the supervised fine-tune, ready to use, and
`-sft-distilled` the 8-step distillation of it. Checkpoints without `-sft` are
base models meant for fine-tuning. `prx-1024-beta` is Photoroom's 1024
preview. PRX Pixel bundles a Qwen3-VL text encoder and has no autoencoder.

## Export

| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Image generation |  |  |  |  |  |  |  |  |  |  |  |  |  |

A "yes" means the export is supported. An empty cell means the exporter refuses that combination.

`export()`, `train()` and `val()` raise, as for every LibreGen family.

## Licensing

Check the license on the Hugging Face repository of the specific weights you download. That repository is authoritative and licenses are not always uniform across a family. This is a description of the licenses involved, not legal advice.

- Original work: PRX and PRX Pixel, Photoroom
- Upstream license: Apache-2.0
- Upstream source: https://github.com/Photoroom/PRX
- LibreYOLO code: MIT
- Weights: Apache-2.0, republished at https://huggingface.co/LibreYOLO
- Interpretation: Photoroom releases the PRX and PRX Pixel weights under Apache-2.0, a permissive license, so they can be used in commercial and closed-source products; redistributing them means keeping the license text and notices, and the license grants a patent license. The exception is PRX's bundled T5Gemma 2B text encoder, which stays under Google's Gemma Terms of Use and the Gemma Prohibited Use Policy: commercial use is allowed, but the prohibited uses pass on to anyone you share it with, and PRX's model cards forbid those uses for the whole model. PRX's autoencoder is the FLUX.1 [schnell] VAE (Apache-2.0) or DC-AE (MIT); PRX Pixel has no autoencoder and bundles the Qwen3-VL-Embedding-2B text encoder (Apache-2.0). LibreYOLO's adapter is its own MIT code that calls the Apache-2.0 diffusers PRXPipeline and PRXPixelPipeline; no upstream source is ported. Weights download from LibreYOLO's byte-identical mirrors of Photoroom's nine PRX repositories and prxpixel-t2i (LibreYOLO/LibrePRX<size> and LibreYOLO/LibrePRXPixel7b), each pinned to a commit and not gated.

PRX and PRX Pixel are by [Photoroom](https://github.com/Photoroom/PRX). The
weights are Apache-2.0, so commercial use is fine. The exception is PRX's
bundled T5Gemma 2B text encoder, which stays under Google's **Gemma Terms of
Use** and Prohibited Use Policy: commercial use is allowed, but the
prohibited uses pass on to anyone you share it with, and PRX's model cards
forbid them for the whole model. The autoencoder is the FLUX.1 [schnell] VAE
(Apache-2.0) or DC-AE (MIT); PRX Pixel's Qwen3-VL-Embedding-2B text encoder
is Apache-2.0.

LibreYOLO's adapter is its own MIT code on the Apache-2.0 diffusers
`PRXPipeline` and `PRXPixelPipeline`. Weights download from
`LibreYOLO/LibrePRX<size>` and `LibreYOLO/LibrePRXPixel7b`, byte-identical
mirrors pinned to a commit, not gated.

## Citation

```bibtex
@misc{photoroom2026prx,
  title  = {PRX: an open-source text-to-image model},
  author = {Bertoin, David and Frigg, Roman and Almazán, Jon and Andres, Eliot},
  year   = {2026},
  url    = {https://huggingface.co/blog/Photoroom/prx-open-source-t2i-model},
}
```

Copied from https://github.com/Photoroom/PRX#citation
