1. You can have it mix and match text and image gen inside a single output. There are so many places this can be useful. Its also able to generate any image, not just cartoons.
MULTIMODAL AI
-
Gemini 2.0 Flash Enables Conversational Image Editing
By
–
2. Conversational image generation Gemini 2.0 Flash helps you edit images through many turns of a natural language dialogue, great for iterating towards a perfect image, or to explore different ideas together.
-
Gemini 2.0 Flash Enables Native Image Generation for Creative Content
By
–
Gemini 2.0 Flash now has native image generation 🤯
— Linus ✦ Ekenstam (@LinusEkenstam) 12 mars 2025
So this is actually pretty wild, I made a short kids story with images from a simple prompt.
Sure the story is simple, but this is so powerful.
🧵 A thread pic.twitter.com/jokgMswUWDGemini 2.0 Flash now has native image generation So this is actually pretty wild, I made a short kids story with images from a simple prompt. Sure the story is simple, but this is so powerful. A thread
-
ChaTS-PI: Generative AI Model for Chart Analysis and Verification
By
–
Stop by the #KHIPU2025 Google booth today at 15:30, where Julian Eisenschlos will demo ChaTS-PI, a generative AI model that takes a chart, generates a summary, and then uses a critic model to verify and revise the summaries for accuracy.
-
Gemini 2.0 Flash Native Image Generation Debuts
By
–
Gemini 2.0 Flash debuts native image gen! Create contextually relevant images, edit conversationally, and generate long text in images. All totally optimized for chat iteration.
— Oriol Vinyals (@OriolVinyalsML) 12 mars 2025
Try it in AI Studio or Gemini API. Blog: https://t.co/pkeRzaD8b5 pic.twitter.com/c7QUzNfC4kGemini 2.0 Flash debuts native image gen! Create contextually relevant images, edit conversationally, and generate long text in images. All totally optimized for chat iteration. Try it in AI Studio or Gemini API. Blog: https://
developers.googleblog.com/en/experiment-
with-gemini-20-flash-native-image-generation/
… -
Using Meta pretrained weights without training or image tokens
By
–
Hm, did you use the pretrained weights from Meta? Does the model work fine if you don't do any training and don't pass any image tokens?
-
AI Video Generation: Audio Quality Still Lags Behind Visual Output
By
–
s look good when on mute. But, with audio, it’s still just not there yet. Looks/sounds like an AI voice dubbed over a real video. Excited to see the progress though!
-
Gemini 2.0 Flash Experimental Multimodal Image Output Launched
By
–
BREAKING : Gemini 2.0 Flash Experimental multimodal image output is rolling out on AI Studio. Google is the 1st lab rolling it out h/t @legit_api
-
Luma Labs Breakthrough: Inductive Moment Matching Improves Image Generation
By
–
Luma Labs introduced a new pre-training technique called Inductive Moment Matching
— Rowan Cheung (@rowancheung) 12 mars 2025
It produces superior image generation quality 10x more efficiently than current approaches
Luma says the approach breaks the algorithmic ceiling of diffusion models!pic.twitter.com/h0x8kG18i4Luma Labs introduced a new pre-training technique called Inductive Moment Matching It produces superior image generation quality 10x more efficiently than current approaches Luma says the approach breaks the algorithmic ceiling of diffusion models!
-
AI Model Accelerates Cancer Therapy Research Through Organoid Analysis
By
–
AI is helping researchers identify therapies for cancer patients. @orakldotbio trained our DINOv2 model on organoid images to more accurately predict patient responses in clinical settings. This approach outperformed specialized models and is helping accelerate their research. pic.twitter.com/7ptP6RcyL3
— AI at Meta (@AIatMeta) 11 mars 2025AI is helping researchers identify therapies for cancer patients. @orakldotbio trained our DINOv2 model on organoid images to more accurately predict patient responses in clinical settings. This approach outperformed specialized models and is helping accelerate their research.