🎨 Image & Video Generation

Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.

1,210 articles

Five free AI video generators suited to beginners

AI video generation has advanced rapidly in a short time. Where professional-looking video once required a camera and editing skills, beginners can now get results from free tools. Source: daily-sun.com

Bandicam debuts Super Narrator, a text-to-video tool for videos up to 30 minutes

Bandicam launched Super Narrator, an AI tool that chains multiple models in a single workflow to produce narrated videos. It targets long-form content with lengths of up to 30 minutes. Source: einpresswire.com

Adobe Firefly turns text prompts into commercial-ready images for free

A 2026 how-to guide explains how Adobe Firefly converts text prompts into realistic images quickly and at no cost. The results can be sized for ads and social posts and used commercially. Source: cnet.com

The 10 best AI video generation APIs, ranked for November 2026

An AI video generation API lets an application create or edit video without sending users to a separate creative site. The roundup compares ten services and what a good one needs to deliver. Source: unite.ai

FUGenerator: multimodal AI platform links architectural concepts to fabrication

Researchers introduced FUGenerator, a multimodal AI platform that combines knowledge graphs with traceable node-based workflows. It aims to streamline the path from architectural concepts to physical fabrication. Source: bioengineer.org

NVIDIA Nemotron 3.5 Super VL lands in Amazon SageMaker JumpStart

AWS has made NVIDIA's Nemotron 3.5 Super VL available through Amazon SageMaker JumpStart. Users can deploy the model in just a few steps directly from SageMaker Studio. Source: aws.amazon.com

ByteDance rolls out Seedream 5.5 as the AI image generation race heats up

ByteDance has released its Seedream 5.5 image model amid a new phase of competition among tech companies building ever more capable image-generation systems. Source: tekedia.com

ByteDance launches Seedream 5.5: 40% faster generation, API price cut in half

ByteDance released its Seedream 5.5 image model on November 9, integrating it at once into Doubao, Doubao Work and Jimeng. The update reportedly speeds up generation by 40% and halves API pricing. Source: finance.biggo.com

How text-to-image AI generators work, plus 5 tools worth trying

Type a prompt like a lighthouse on a cliff at dusk, and within seconds an image that never existed appears. The piece explains how these generators work and highlights five tools that deliver good results. Source: sitepoint.com

Guide to Adobe Firefly text-to-video: generate clips, animate stills, extend footage in Premiere Pro

A practical guide to using Adobe Firefly's generative AI tools to streamline video editing, from creating AI video to animating still images and extending clips in Premiere Pro. Source: au.pcmag.com

Linum-AI's experimental P-JiT 21K text-to-image model under the hood

A look at Linum-AI's P-JiT 21K text-to-image model, covering its architecture, training specifications, known limitations and how to set it up for generation. Source: hackernoon.com

Linum releases P-JiT, an ultra-cheap image generation model, as open weights

Linum, a two-person AI research group, has unveiled its image generation model Pyramid-JiT (P-JiT). The model is designed to overcome two major hurdles in image generation by training efficiently at very low cost, and its weights are now openly available. Source: gigazine.net

Inside Viggle Remake: LoRA-based video editing powered by MiniMax-H3

A closer look at Viggle Remake's AI video editing features, built on a LoRA architecture. The overview covers character swapping, reference frames, GPU requirements, and the tool's current limitations. Source: hackernoon.com

AI Week in Review: A Flood of New Model Releases

This weekly roundup covers a batch of fresh releases, including Images 2.6, Gemini Omni 1.2 Flash, Pika H3 Flex, Hy4, Kimi K3.1 Pro model weights, Inkling 2 Small, Ripple-65B Preview, SWE-2 Flash and GPT-6 Cyber. The snippet is truncated, so further items on the list are not visible. Source: patmcguinness.substack.com

DomoAI Adds MCP and CLI, Bringing Media Generation to Codex and Claude

DomoAI has launched MCP and CLI support, letting users generate videos, images and audio directly from Codex and Claude. The move follows a growing trend of delegating tasks such as writing, research and programming to AI. Source: saiganak.com

Turning Text Into Images With Adobe Firefly: A 2026 How-To

Adobe Firefly offers a quick and free way to convert text prompts into realistic images. The guide explains how to size the results for ads and social posts and use them commercially. Source: tech.yahoo.com

Best Free AI Video Generators of 2026, Tested Without Watermarks

A hands-on comparison of free AI video generators in 2026 that need no credit card and leave no watermark. It covers both text-to-video and image-to-video tools you can use to make clips right away. Source: felloai.com

FLUX 3 Image Klein gets a speed boost on NVIDIA Blackwell GPUs

NVIDIA's technical blog describes how to accelerate image generation with FLUX 3 Image Klein on Blackwell GPUs. Inference latency is a key concern when diffusion models are deployed in design tools, image editors, and visual production workflows. Source: developer.nvidia.com

ChatGPT Images 2.6: specs, benchmarks, pricing and rivals compared

An overview of ChatGPT Images 2.6 covers its features, the API pricing of the Sunburst and Flare models, and availability. It also discusses the limitations of current benchmarks and how the model stacks up against competing image generators. Source: google.com

AIVideoFree adds OpenAI's GPT Image 2.6 one day after launch

The platform integrated the new Sunburst and Flare models and now runs them alongside competing image generators. It also ran a side-by-side text-rendering test against other image models. Source: google.com