Avataar AI Launches Low-Cost Varya Video Model for India
TechCrunch AI2 days agoReleaseAvataar AI has launched Varya, a video generation model built from Alibaba’s open Wan 2.2 model and distilled for faster, cheaper output. The company says Varya can generate 5-second 720p clips on an NVIDIA H200 in 45 seconds, versus 1,230 seconds for Wan 2.2. Avataar plans to release the model and training data through India’s AI Kosh portal while offering hosted access at about $0.005 per second.
Grok Imagine Video 1.5 on AI Gateway
Vercel Changelog11 days agoReleaseVercel’s changelog points to Grok Imagine Video 1.5 becoming available through AI Gateway. The public model page lists the preview model as xai/grok-imagine-video-1.5-preview and marks it primarily for image-to-video generation. Because the source text is unavailable, concrete claims about quality, speed, audio, editing, or text-to-video improvements should not be inferred.
How to Prompt Grok Imagine Video 1.5
Replicate Blog24 days agoTutorialxAI has released Grok Imagine Video 1.5, a model that animates a still image into a short video clip. It generates synchronized audio during the same pass, combining visual animation and sound creation in one workflow. The Replicate Blog post focuses on prompting techniques intended to help users get more from the model.
Fuel your creativity with new generative media models and tools★ 78
Google DeepMind Blog390 days agoNew ToolGoogle announced new generative media models and tools at I/O 2025, led by Veo 3 for video, Imagen 4 for images, and Flow for AI filmmaking. Veo 3 adds audio generation, while Imagen 4 improves detail, typography, aspect ratios, and up to 2K output. Google also expanded Lyria 2 and Lyria RealTime access, while continuing SynthID watermarking and launching SynthID Detector.