Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

C3.ai Just Nabbed a Bigger Air Force Contract. Should You Buy AI Stock Here?

Paper page – FLEXITOKENS: Flexible Tokenization for Evolving Language Models

OpenAI launches a full-fledged ChatGPT agent which can work without supervision

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Industry AI
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Voice/Audio Generation

Firefly adds new video capabilities, industry leading AI models, and Generate Sound Effects feature

By Advanced AI EditorJuly 18, 2025No Comments7 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Screenshot of Firefly's new video capabilities.

Today, we’re introducing powerful enhancements to our Firefly Video Model, including improved motion fidelity and advanced video controls that will accelerate your workflows and provide the precision and style you need to elevate your storytelling. We are also adding new generative AI partner models within Generate Video on Firefly, giving you the power to choose which model works best for your creative needs across image, video and sound.

Plus, our new workflow tools put you in control of your video’s composition and style. You can now layer in custom-generated sound effects right inside the Firefly web app — and start experimenting with AI-powered avatar-led videos.

Improving the Firefly model and expanding options

Among the strengths of the Firefly Video Model is generating dynamic landscapes, from natural vistas to urban environments. The model also demonstrates remarkable capability with animal motion and behavior, atmospheric elements like weather patterns and particle effects, and both 2D and 3D animation. The Video Model’s newly improved motion fidelity means your video generations will now move more naturally, with smoother transitions and lifelike accuracy.

Let’s take a look at these new enhancements in action — the generations shown below were created with our Firefly Video Model.

Prompt: Cinematic drone shot going between the trees of a snowy forest at sunset golden hour. The lighting is cinematic and gorgeous and soft and sun-kissed, with golden backlight and dreamy bokeh and lens flares. The color grade is cinematic and magical. shot on film. Drone shot smooth camera, aerial cinematography. Snow is falling gently.

Prompt: A macro close-up of an octopus nestled among coral, its skin shifting color and texture in real time. The lighting is dappled and dynamic — shafts of sunlight filter through the water’s surface, casting rippling patterns across its body. In the foreground, blurred coral branches and swaying seaweed frame the shot, adding depth and movement. The camera lingers on a single eye, intelligent and alien, as its tentacles curl slowly in the current. Microbubbles drift past the lens, catching the light in shimmering flares. The color grade is rich and aquatic — deep teals, coral reds, and flashes of iridescent blue. The mood is hypnotic, intelligent, and otherworldly.

Prompt: The adorable kid runs towards the camera; reference image generated on Firefly.

Creators enjoy experimenting with different styles, so we’re continuously expanding the models we offer inside the Firefly app. Recently, we added Runway’s Gen-4 Video and Google Veo3 with Audio to Firefly Boards and Veo3 with Audio in Generate Video. And there are more partner models coming soon to the Firefly app:

Topaz Labs’ Image and Video Upscalers and Moonvalley’s Marey will be launching soon in Firefly Boards.
Luma AI’s Ray 2 and Pika 2.2, which are already available in Boards, will soon be added to Generate Video.

From storyboarding to fully animated video outputs, Firefly web and mobile apps let you choose the AI model that best fits each part of your workflow, while keeping your style consistent and creative control intact.

Direct every detail with advanced video controls

Today’s release also provides you with a new level of creative precision in directing your video content. Whether you’re creating for mobile, widescreen, or social, you can easily select vertical, horizontal, or square aspect ratios to match your format — no extra editing required.

We’re also introducing other powerful new features designed to save you time and elevate your creative output:

Composition Reference for Video

Bring structure and consistency to your video creations. Upload a reference video, describe your vision, and Firefly will generate a new video that transfers the original composition to your generation — perfect for maintaining visual flow across scenes or repurposing existing content with a fresh look.

Image of Firefly's new video capabilities including a prompt.

Prompt: A man is performing a yoga pose in a bright, airy tropical studio.

Style Presets

Apply a distinct visual style to your video with a single click. Choose from presets like claymation, anime, line art, or 2D to instantly set the tone. Whether you’re pitching a concept, building a creative brief, or finalizing your output, Style Presets help you stay consistent and speed up your workflow.

Keyframe Cropping

Stay in your creative flow with intuitive cropping tools. Upload your first and last frames, select how your image will be cropped, describe your scene, and Firefly will generate a video that fits your format — no need to jump between tools. It’s fast, flexible, and designed to match your vision from start to finish, while keeping your creative process effortless.

Image of Firefly's new video capabilities including a prompt.

Prompt: A close-up of a cute, glossy red bird perched on a soft, white, plush material.

Composition Reference, Style Presets, and Keyframe Cropping are built to give you more control, more speed, and more creative freedom. And they’re just the beginning. Even more enhancements are on the way to help you push your storytelling further.

Bring your stories to life with sound effects and virtual avatars

Whether you’re building a tutorial, pitching a concept, or creating content at scale, Firefly now gives you even more ways to enhance your storytelling with two new features. With our commercially safe Generate Sound Effects (beta), you can layer in custom audio using just a prompt or your voice, adding emotion, energy, and cinematic polish to every scene. And with Text to Avatar (beta), you can turn scripts into avatar-led videos with just a few clicks.

Generate Sound Effects (beta)

Sound is a powerful storytelling tool that adds emotion and depth to your videos. Generate Sound Effects (beta) makes it easy to create custom sounds, like a lion’s roar or ambient nature sounds, that enhance your visuals. And like our other Firefly generative AI models, Generate Sound Effects (beta) is commercially safe, so you can create with confidence.

Just type a simple text prompt to generate the sound effect you need. Want even more control? Use your voice to guide the timing and intensity of the sound. Firefly listens to the energy and rhythm of your voice to place sound effects precisely where they belong — matching the action in your video with cinematic timing.

Once your video is complete, you can export directly to Adobe Express to create polished, share-ready content for all your social channels or export to Premiere Pro to add the video into your existing timeline.

Text to avatar (beta)

With Text to avatar (beta), you can turn your scripts into engaging, avatar-led videos in just a few clicks.

Choose from a diverse library of avatars, customize your background with a color, image, or video, and select the accent that best fits your video. Firefly handles the rest.

Here are a few ways creators are using Text to avatar:

Delivering clear, engaging video lessons or FAQs with a virtual presenter
Transforming blog posts or articles into scalable video content for social media
Pitching ideas or building internal training materials with a human touch.

Whether you’re educating, informing, or inspiring, Text to avatar helps you bring your message to life — quickly, consistently, and at scale.

Create faster, with less guesswork

We know crafting the perfect text prompt can sometimes slow you down. You don’t want to have to create different versions of the same prompt just to get what you want.

That’s why we’re introducing Enhance Prompt within the Generate Video module on Firefly web, a new feature designed to help you get better results faster. Enhance Prompt takes your original input and adds language that helps Firefly better understand your creative intent. It removes ambiguity, sharpens direction, and speeds your workflow — so you can spend less time tweaking and more time creating.

Commercially safe, production ready

We believe that generative AI can be developed responsibly, starting with respect for creators’ rights. Our commercially safe family of Adobe Firefly generative AI models is trained only on assets we have permission to use and we never train on the content you produce in our tools.

Help when you need it

We’re excited to see you produce stellar videos, and we offer help if you need it. Our Firefly User Guide will take you from zero to creating in minutes. Learn how to write better prompts with our field-tested best practices, explore step-by-step tutorials, and dive deeper into features like Composition Reference and Style Presets. Plus, stay up-to-date with everything new in Firefly.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleSports teams adopt 5G and data solutions
Next Article Perplexity sees India as a shortcut in its race against OpenAI
Advanced AI Editor
  • Website

Related Posts

Exclusive: Krisp launches VIVA development kit to enhance accuracy for voice AI agents

July 16, 2025

Cockpit audio deepens mystery of Flight 171

July 12, 2025

LVO) Partners with Synervoz for Voice AI

July 4, 2025

Comments are closed.

Latest Posts

Yale Art Gallery Rejects Federal Grants for Africa Migration Show

With NEA Funding Slashed, Black Arts Institutions Face a Tough Future

Erotic Mosaic Held by Nazi Officer Goes on View in Pompeii

Chanel Will Return to New York City with Métiers d’Art Collection

Latest Posts

C3.ai Just Nabbed a Bigger Air Force Contract. Should You Buy AI Stock Here?

July 18, 2025

Paper page – FLEXITOKENS: Flexible Tokenization for Evolving Language Models

July 18, 2025

OpenAI launches a full-fledged ChatGPT agent which can work without supervision

July 18, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • C3.ai Just Nabbed a Bigger Air Force Contract. Should You Buy AI Stock Here?
  • Paper page – FLEXITOKENS: Flexible Tokenization for Evolving Language Models
  • OpenAI launches a full-fledged ChatGPT agent which can work without supervision
  • Startup Typedef gets $5.5M seed funding to build customized data pipelines for AI model workloads
  • SoulGen Launches Revolutionary Image to Video AI Platform

Recent Comments

  1. Bonus de parrainage Binance on University of Tokyo to upgrade its IBM quantum computer with 156-qubit Heron QPU
  2. binance on Is C3.ai a Phenomenal Under-the-Radar AI Stock?
  3. melhor código de indicac~ao binance on Google DeepMind develops AlphaEvolve AI agent optimized for coding and math
  4. aviator official website on Former Tesla AI czar Andrej Karpathy coins ‘vibe coding’: Here’s what it means
  5. BitStarz on Former Tesla AI czar Andrej Karpathy coins ‘vibe coding’: Here’s what it means

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.