Model reference · open weights
prxpixel-t2i is an open-weight image model from Photoroom. prxpixel-t2i (BF16) weighs 17.4 GB; the smallest configuration that runs it is RTX 4090 24 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the Photoroom/prxpixel-t2i model card, 2026-10-01
What it is
| Released by | Photoroom |
|---|---|
| Released | 2026-06-11 |
| Parameters | 7.0B |
| VRAM | 17.4 GB for the weights |
What it runs on
| Card | One image | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4060 Ti 16 GB | does not fit | |
| RTX 3090 24 GB | tight | 23.4 GB |
| RTX 4090 24 GB | tight | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
PRXPixel is a pixel-space variant of PRX:
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.
torch.bfloat16Qwen3VLTextModel)FlowMatchEulerDiscreteScheduler[!IMPORTANT]
PRXPixelPipelineis not yet in a releaseddiffusers. Installdiffusersfrom the branch that adds it, and usetransformers >= 4.57(the version that introducedQwen3VLTextModel):pip install "transformers>=4.57" pip install "git+https://github.com/huggingface/diffusers.git@prx-pixel-pipeline"
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")
Released under the Apache 2.0 license. See LICENSE and NOTICE.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. Runs as it is with diffusers, on the machine, in Python.
# on your rented machine: pip install diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained("Photoroom/prxpixel-t2i", torch_dtype=torch.bfloat16).to("cuda")
image = pipe(prompt="a red bicycle on a cobbled street").images[0]
image.save("/workspace/out.png")