DeepFloyd IF
An early model that was among the first to render text on images accurately. Today it is mostly of historical interest; development has stopped.
The last open version came out in Apr 2023. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.
- Developer
- DeepFloyd (Stability AI), UK
- First release
- Apr 2023
- Latest release
- Apr 2023
- Sizes
- 0.4B – 4.3B
- License
- Non-commercial onlyDeepFloyd IF License — research only, commercial use prohibited
- Running
- On your own serverNeeds a GPU
- Industries
- Science and research
What it does
- Research experiments
- Prototype images with captions
Where it is used
Hardware requirements
Versions
- IF-I-XL v1.0
- IF-I-M / IF-I-L
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can DeepFloyd IF be used in a commercial project?
No. License: DeepFloyd IF License — research only, commercial use prohibited. A commercial product needs a different model or a separate agreement with the rights holder.
What hardware does DeepFloyd IF need?
At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does DeepFloyd IF support Russian?
Language does not matter for this model: it does not work with text.
Where can I download DeepFloyd IF and what does it cost?
The DeepFloyd IF weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
The model that started open image generation. A huge ecosystem of fine-tunes, styles and plugins; runs even on a home PC. The popular SDXL-Lightning and Hyper-SD accelerators were made by ByteDance.
DetailsImage generationPixArtHuawei Noah's Ark Lab and partners · ChinaCommercial use allowedA compact 0.6B image model with quality on par with much larger ones. The Sigma version does 4K; suits modest hardware.
DetailsSource: huggingface.co/DeepFloyd/IF-I-XL-v1.0. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


