AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity

Update docs/source/en/api/pipelines/photon.md

Browse Source 
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
This commit is contained in:
David Bertoin
2025-10-16 10:48:24 +02:00
committed by DavidBert
parent 0fdfd27ecb
commit 34a74928ac
1 changed files with 1 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/source/en/api/pipelines/photon.md
View File

@@ -15,15 +15,7 @@
# PhotonPipeline
Photon is a text-to-image diffusion model using simplified MMDIT architecture with flow matching for efficient high-quality image generation. The model uses T5Gemma as the text encoder and supports either Flux VAE (AutoencoderKL) or DC-AE (AutoencoderDC) for latent compression.
Key features:
- **Simplified MMDIT architecture**: Uses a simplified MMDIT architecture for image generation where text tokens are not updated through the transformer blocks
- **Flow Matching**: Employs flow matching with discrete scheduling for efficient sampling
- **Flexible VAE Support**: Compatible with both Flux VAE (8x compression, 16 latent channels) and DC-AE (32x compression, 32 latent channels)
- **T5Gemma Text Encoder**: Uses Google's T5Gemma-2B-2B-UL2 model for text encoding offering multiple language support
- **Efficient Architecture**: ~1.3B parameters in the transformer, enabling fast inference while maintaining quality
Photon generates high-quality images from text using a simplified MMDIT architecture where text tokens don't update through transformer blocks. It employs flow matching with discrete scheduling for efficient sampling and uses Google's T5Gemma-2B-2B-UL2 model for multi-language text encoding. The ~1.3B parameter transformer delivers fast inference without sacrificing quality. You can choose between Flux VAE (8x compression, 16 latent channels) for balanced quality and speed or DC-AE (32x compression, 32 latent channels) for latent compression and faster processing.
## Available models:
We offer a range of **Photon models** featuring different **VAE configurations**, each optimized for generating images at various resolutions.