AI Video Tools You Can Use Today
The latest AI video models that deliver results
Total reading time around 5 minutes.
Welcome to Visually AI!
🔮AI News this Week
Top AI video tools
AI video models are improving so quickly, I can barely keep up! I wrote about unreleased Adobe Firefly Video in the last issue, and we are no closer to public access to Sora.
No worries - we do have plenty of generative AI video tools we can use right now.
Kling AI launched its updated v1.5 and the quality of image or text to video is impressive.
Hailuo MiniMax text to video remains free to use for now, and it produces natural and photorealistic results (with watermarks).
Runway added the option to upload portrait aspect ratio images to generate vertical videos in Gen-3 Alpha & Turbo modes.
Luma AI launched the Dream Machine API - which has been added to multiple platforms and apps, including Fal, HuggingFace (need a Luma API key), Hunch, and many more.
And there are plenty more video apps, including PixVerse, Haiper, Stable Video, and others.
Right now, there are several capable of producing high quality results, like the examples below.
I used the same text-only prompt for each of these video models: Gen-3, Kling AI 1.5, PixVerse, Hailuo MiniMax.
Prompt: “Close-up of a woman with curly hair, her lips parting slightly as if about to speak. She has a serious look on her face as she thinks about a difficult decision, but she slowly looks relieved and relaxed. Trees in background gradually shift from soft focus to sharp as she moves. Cinematic color grading, with dark cyans, cool blues in the style of a blockbuster thriller”
To be fair, I could use any of these results.
What do you think? Do you see a clear favorite?
This example shows image to video quality between Runway’s Gen-3 and Kling AI 1.5.
I ran each image in both video models with no prompt to compare the results. The top image was generated with Mystic v2 in Magnific, and the bottom image is from Midjourney using my new model personalization code.
Overall, I was satisfied with each result. There were slight differences and it depends on your personal preferences.
I think it’s great that we have choices, from free plans to professional subscriptions - and they are currently available for anyone to use if they choose.
Meta News
Llama 3.2: Meta launched Llama 3.2, its latest large language model, which includes multimodal vision models capable of understanding both images and text, and is available in various sizes for different applications, including lightweight versions for mobile and edge devices.
Meta Glasses: Meta’s Ray-Ban smart glasses are updated with new AI features, including real-time video processing, live language translation, reminders, QR code scanning, and integrations with iHeart Radio and Audible, aiming to create a more natural and practical AI assistant experience.
Orion AR Glasses: Meta unveiled its Orion AR glasses prototype, featuring a compact design and the ability to superimpose digital visuals onto the physical world, including holographic apps and real-time object recognition, marking a significant step towards next-generation personal computing for the metaverse.
📸AI Snapshots
OpenAI rolled out Advanced Voice Mode for ChatGPT, offering a more natural conversational experience with nine voice options, improved accent understanding, and faster responses, available to Plus, Team, and Enterprise plan subscribers. Advanced Voice is also available in the U.K, but not in the EU, Switzerland, Iceland, Norway, and Liechtenstein.
Leonardo AI introduced Ultra Mode to simplify and speed up workflows, to make generations much faster, cheaper, and better quality. You will see Ultra Mode throughout the platform for image generation and upscaling.
RunwayML announced its new API for generative video for individuals and teams - apply for access here.
Mystic v2 in Magnific: Generate images with Magnific AI up to 4k resolution. New settings include Realism, Aspect ratio, and Creative detailing. The results are impressive:
Krea AI Flux Folders & Assets: Organize Flux generations and search through your images quickly. (link)
🛠️ This Week’s AI Tools
Hunch: AI-powered workspace lets you combine multi-modal blocks to accomplish complex tasks. (link)
Pinokio: Install, run, and control apps, bots, servers, databases, and more on your computer with one click. (link)
Sezam: Generate quality images on demand based on Sezam styles (photos, illustrations, logos, or company’s visual assets. Several models available, including FLUX. (link)
Blaze Designer: AI-powered content platform added a simplified Designer to generate, plan, and schedule up to 60 posts in minutes. (link)
Miniature People FLUX LoRA: Generate realistic images with miniature people on Civitai with ILikeToasters’ LoRA. (link)
Vimmerse: Generate 3D videos from your product photos. (link)
BBC Sound Effects Library: Search and download 16,000 sound effects and field recordings for free. (link)
Qreates: Upload your product image and generate photorealistic shots in any scene, with your logo and text intact, by Salma. (link)
Visually AI on YouTube
I’ve been working on several personal and client projects, so I haven’t been much on YouTube. These are two short videos comparing AI video results and editing effects I’m learning:
🖼️ Image Prompts
Prompt: A woman standing on a cliff at sunset, wearing a black blazer and sunglasses, with the sun setting in the background.
Prompt: Glistening jar of golden honey, amber-hued wooden dipper dripping sweetness. Vibrant lemon slices scatter, their zesty aroma mingling with fresh mint sprigs. Bathed in soft sunlight, the scene radiates on pristine white. Hyper-realistic details capture every reflection, texture, and droplet, evoking nostalgic warmth.
🎬Video Prompt
Prompt: Tracking close-up shot of a glass of white wine catching the golden sunlight on a beautifully set dining table. Soft, diffused lighting enhances the warm and inviting atmosphere.
Generated on Kling AI 1.5:
Thanks for reading and have a creative week!