DiffusionGemma
DiffusionGemma is Google’s open experimental 26B MoE text-diffusion model for faster local text generation, parallel editing, code infilling, and non-linear text workflows.
- Type
- Multimodal
- Weights
- Open
- Downloads
- 613k
- Likes
- 1.3k
- Pipeline
- image text to text
- License
- apache-2.0
Model hub
google/diffusiongemma-26B-A4B-it
- Repo
- google/diffusiongemma-26B-A4B-it
- Library
- transformers
- Access
- Public
Technical tags and languages
More from Google
11
-
Bard
Text
Bard is Google’s early conversational assistant. It answers questions, writes and rewrites text, and pulls in…
-
CameraTrapAI
Multimodal
Google-provided AI models for classifying wildlife species in camera trap images.
-
Chirp 3
Audio
Chirp 3 is Google's latest multilingual automatic speech recognition (ASR) transcription model, offering high…
-
Code Wiki
Multimodal
Code Wiki is Google’s AI-powered platform that turns code repositories into a living wiki, automatically gene…
-
D4RT
Coding
D4RT is DeepMind’s unified 4D scene reconstruction and tracking model that turns ordinary videos into a fast,…
-
DreamFusion
Image
AI model by Google
-
Flan-T5
Text
AI model by Google
-
Gemini 3.5 Flash Cyber
Coding
Gemini 3.5 Flash Cyber is a lightweight cybersecurity model built on Gemini 3.5 Flash and fine tuned to find,…
About Google
1
At Google, we think that AI can meaningfully improve people's lives and that the biggest impact will come when everyone can access it.