Create
Release-by-release coverage of the AI creation stack: video, image, music, voice, design and code generation tools.
Release-by-release coverage of the AI creation stack: video, image, music, voice, design and code generation tools.
Latest in Create
30 stories
Figma bets on human judgment at Config 2026 while the AI powering its canvas belongs to someone else
At Config 2026, Figma turned its canvas into a full workspace with code, animation, shaders, and AI agents. But the intelligence powering all of it is rented fr…
How Loka Built a Natural, Low-Latency Voice Agent with Amazon Nova 2 Sonic
In this post, we demonstrate the architecture and approach Loka used to solve a common frustration: robotic, slow voice assistants that cause customers to hang …
Information-Theoretic Classifier-Free Guidance with Adaptive Schedule Optimization
Diffusion models have achieved strong performance in image, text-to-image, and video generation, where conditional generation is often controlled by classifier-…
EPEdit: Redefining Image Editing with Generative AI and User-Centric Design
The demand for image manipulation has seen a significant increase recently. Traditional tools like Photoshop and Capture One, while powerful, require considerab…
DramaDirector: Geometry-Guided Short Drama Generation
Short dramas, with their rapid shot rhythms, dialogue-driven focus shifts, and demanding cinematographic grounding, pose challenges that prompt-level or text-on…
ZONOS2 Technical Report
We present ZONOS2 8B, our latest TTS model, which achieves state-of-the-art naturalness, prosody, and voice cloning fidelity. We improve upon Zonos-v0.1 across …
S1-Omni-Image: A Unified Model for Scientific Image Understanding, Generation, and Editing
We present S1-Omni-Image, an open-weight unified multimodal model for scientific image understanding, generation, and editing. Unlike general-purpose image gene…
CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation
Chinese news text contains dense written forms such as scores, hyphenated model names, ranges, unit symbols, percentages, English abbreviations, and mixed Chine…
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods imp…
Build a protein research copilot with Amazon Bedrock AgentCore
This post shows you how to build a conversational protein research assistant that combines three capabilities: Natural language query parsing to extract structu…
Cursor announces its own AI model, a new Git platform, and a mobile app
Cursor has revealed new details about its first AI model trained entirely in-house and announced two new products. The article Cursor announces its own AI model…
ByteDance's Seedance 2.5 breaks the 30-second barrier for AI video generation
ByteDance introduced five new AI models at Volcano Engine's FORCE conference. The centerpiece is Seedance 2.5, a video model set to launch in early July. The ar…
AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions
Agentic artificial intelligence (AI) systems are beginning to assist, accelerate, and partially automate scientific discovery, performing tasks that span litera…
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
Recent diffusion-based models have enabled realistic audio-driven avatar generation in real-time streaming. However, existing approaches struggle to maintain vi…
RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation
Recent years have witnessed remarkable progress in image generation and editing, particularly regarding instruction following and visual fidelity. However, when…
The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection
Provenance watermarking is increasingly treated as a safeguard for synthetic speech, whether built directly into speech-generation models such as Chatterbox, pr…
Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping
Reference-based diffusion models enable highly controllable image generation by leveraging elements from input images to guide prompt-driven synthesis. However,…
Running ComfyUI workflows on Amazon SageMaker AI processing jobs
In this post, we walk you through how to deploy ComfyUI workflows on Amazon SageMaker AI processing jobs to generate hundreds of high-quality images in a single…
LooseControlVideo: Directorial Video Control using Spatial Blocking
Precise 3D spatial orchestration in text-to-video generation remains a significant challenge, particularly for multi-object scenes where semantic layout and tem…
Amazon drops its OpenAI drama film after signing a $50 billion deal with Sam Altman's company
Amazon MGM Studios has dropped "Artificial," the nearly finished OpenAI film directed by Luca Guadagnino with Andrew Garfield as Sam Altman. Amazon struck a $50…
Adobe adds AI agents to Photoshop, Premiere, and more Creative Cloud apps
Adobe is rolling out its "creative agent" across its main Creative Cloud apps and third-party AI platforms like ChatGPT and Claude. Users describe what they wan…
Midjourney, known for AI image generation, unveils a full-body ultrasound scanner and its own spa
Rumors about Midjourney hardware have circulated for years, but nobody saw this coming. The AI image startup is building a full-body ultrasound scanner and open…
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. Howeve…
WHAT THEY ARE SAYING: First Lady Melania Trump Launches Fostering the Future Accounts
Last week, First Lady Melania Trump launched Fostering the Future Accounts, a new financial resource established to empower foster youth to be fiscally aut…
Microsoft's Copilot Cowork moves to usage-based billing and may tap DeepSeek
Microsoft is weighing a fine-tuned version of Deepseek V4 as a cheaper model option for Copilot Cowork. The company is also switching to usage-based billing, si…
SpaceX bets $60 billion on Cursor to catch OpenAI and Anthropic
Just two trading days after its IPO, Elon Musk's SpaceX is buying AI coding startup Anysphere. The deal is meant to help the struggling xAI division catch up wi…
Microsoft Research's Mirage gives video generation a persistent spatial memory that doesn't forget what's around the corner
Mirage, a video world model from Microsoft Research and several universities, stores scene information directly in latent space instead of pixel-based point clo…
Announcing Ironwood TPUs General Availability and new Axion VMs to power the age of inference
Today’s frontier models, including Google’s Gemini, Veo, Imagen, and Anthropic’s Claude train and serve on Tensor Processing Units (TPUs). For many organization…
Apply AI Webinar on AI for Cultural, Creative and Media Sectors
Apply AI Webinar on AI for Cultural, Creative and Media Sectors Anonymous (not verified) Tue, 06/02/2026 - 12:29 24 June 2026 This webinar will focus on …
Nano Banana 2 and Nano Banana Pro are generally available, and already powering creative workflows
Organizations are unlocking entirely new ways to use image generation and editing across their industries. To drive next-generation experiences, businesses are …