Lens: Microsoft Diffusion Model with Base + Turbo Variants
ComfyUI Wiki
Lens is Microsoft's diffusion model with base and Turbo variants, using GPT-OSS 20B text encoder and FLUX.2 VAE, repackaged for ComfyUI.
L
Lens
DiffusionImage GenerationMicrosoftTurboMicrosoft Lens is a diffusion model available in base and Turbo variants with MXFP8 quantized options. Requires the GPT-OSS 20B text encoder and FLUX.2 VAE. Repackaged for ComfyUI by Comfy-Org with multiple quantization options.
| Developer | Microsoft |
| Release Date | 2025 |
| Architecture | Diffusion Transformer |
| License | MIT |
| Capabilities | Text-to-image generation |
| Required Text Encoder | GPT-OSS 20B |
| Required VAE | FLUX.2 VAE |
| Variants | Base bf16, Base MXFP8, Turbo bf16, Turbo MXFP8 |
Guides and workflows related to this model series.
No articles found.
Comments
Sign in with GitHub to join the discussion.