Model reference · open weights

IF-I-M

Image DeepFloyd Text→image 1 build Its own licence terms 1k dl/mo

IF-I-M is an open-weight image model from DeepFloyd. IF-I-M-v1.0 (FP32) weighs 10.1 GB; the smallest configuration that runs it is RTX 4090 24 GB.

Request Rent a GPU

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

IF-I-M is a 372M parameter text-to-image model developed by DeepFloyd that serves as the first stage of a cascaded diffusion pipeline.
It generates 64x64 pixel images using a frozen T5 text encoder and a UNet architecture, primarily supporting English and other Romance languages.
The model is released under the deepfloyd-if-license for research purposes.

Summary of the DeepFloyd/IF-I-M-v1.0 model card, 2026-10-01

What it is

What it runs on

Memory and cards for IF-I-M-v1.0 (FP32)

10.1 GBweights, file size

5.0 GBworking memory, one 1024² image

537 MBruntime overhead

How it works

Running it yourself

Rent a machine by the hour. How to run this model is on its model card.

Details