Canva releases first image generation model
TechCrunch: Canva releases its first image generation model
Canva is making its new image model available to all users, promising better, more customizable performance at lower costs.
What happened
Canva launched Canva Craft, its first AI image generation model, making it available to all platform users globally. The model uses a two-stage system that plans spatial relationships and visual hierarchy before generating images up to 2K resolution in various aspect ratios. Unlike competitors, Canva trained the model on human-designed templates from its own library rather than photographs, enabling generated images to have accurate details and legible text.
What each outlet adds
- TechCrunch ↗: The model will work through third-party chatbots, potentially helping Canva reduce API costs while improving quality and speed control.
- The Verge ↗: Canva Craft can generate images in more than 30 aspect ratios and was trained on millions of human-made templates from Canva's platform.
Why it matters
Canva Craft competes directly with image generation models from OpenAI, Microsoft, and Google. The two-stage planning approach allows for greater precision, consistency, and control, particularly for complex images requiring legible text and precise object placement.
Get smart on it
Design platform Canva released its first image generation model called Canva Craft, which competes with similar models from other major tech companies. The model works in two stages: first interpreting user prompts to plan spatial relationships and visual hierarchy, then generating images up to 2K resolution in various aspect ratios. Unlike competitors that use photographs for training, Canva trained its model on human-designed templates from its own library, allowing generated images to have accurate details and legible text that can be precisely edited. The new model is available to all platform users and will also work through third-party chatbots, potentially helping Canva reduce API costs while improving quality and speed control.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time
Mistral AI launched Voxtral 3, a new family of language models built for real-time voice agents. The system combines speech-to-text, text-to-speech, and a voice agent SDK, supports more than 50 languages, and lets agents tap into external tools during live conversations. It can run on your own infrastructure or through EU-hosted APIs to keep data under your control. The article Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time appeared
Also reported by MarkTechPost
Ai2 releases OlmoEarth v1.3 state-of-the-art AI-ready satellite embeddings for the whole planet
Ai2, the Allen Institute for Artificial Intelligence, today released a satellite map embedding model called OlmoEarth v1.3 and precomputed annual embeddings for the whole planet at various resolutions with a browser-based map-making tool. The model compresses a year of satellite observations into a numerical fingerprint for each 10-by-10-meter patch of ground at the smallest resolution, […] The post Ai2 releases OlmoEarth v1.3 state-of-the-art AI-ready satellite embeddings for the whole pl
Also reported by Hugging Face
OpenAI makes its Jev competitor widely available as decision model competition heats up
OpenAI is launching its decision model to the world. Can it compete with the original Jev?
Build more responsive apps with the Decisions API
Fast, focused, low-cost decisions for any application.
Recursive launches Flint, a laptop coding model it says was largely built by AI
Startup Recursive has released Flint, a free, laptop-sized coding model built largely by its own AI research system, as an early test of AI that improves itself.
Also reported by Wired AI and MarkTechPost
Voxtral 3
Voxtral 3: Mistral's voice agent SDK for real-time speech in 50+ languages — accurate transcription, emotional TTS, deep tool use. EU-hosted or self-deployed.