Microsoft Lens

Lens is a 3.8B-parameter foundational text-to-image model designed for efficient training and fast high-resolution generation. It combines dense-caption pre-training, mixed-resolution learning, GPT-OSS multi-layer text features, and the FLUX.2 semantic VAE to reach competitive quality with substantially less training compute than larger T2I models.

Diffusion Model

bf16

https://huggingface.co/Comfy-Org/Lens/tree/main/diffusion_models

fp8

https://huggingface.co/dummy9996/lens-mxfp8-comfyui/tree/main

Encoder

https://huggingface.co/Comfy-Org/Lens/tree/main/text_encoders

Vae

https://huggingface.co/Comfy-Org/Lens/tree/main/vae

requires PR pull:

(run these commands in your "comfyui" folder where models, custom nodes, and output folders reside, NOT ROOT)

git fetch origin pull/14077/head:pr-14077

git checkout pr-14077

once the model is native to comfy, you can just update your comfyui to the latest branch instead of utilizing the PR pull. for now this is what we have. probably today will be the day it gets approved into the master branch.


TURBO MODEL REQUIRES 4 STEPS. DEV MODEL REQUIRES 20 STEPS. workflow is currently set to Dev model settings.



Original Contributor notes:
The model is released for research purposes only and is not intended for product or service deployment. Responsible AI considerations were incorporated throughout the development process, including data selection, model training, and evaluation. The training data includes a combination of public, licensed, and internal datasets that were processed to remove clearly identifiable personal information and reduce harmful content where possible. However, as the data is largely sourced from web-scale collections, it may contain biases or uneven representation. As a result, the model may generate outputs that are inaccurate, biased, or inappropriate under certain prompts, including content that could be misleading or raise copyright or IP-related concerns. Given these limitations, the model should be used in controlled research settings, with appropriate human oversight. Downstream users are responsible for applying additional safeguards, such as content moderation, validation, and compliance checks, before using the model in broader applications.