Loading video...

Video Failed to Load

Go Home

While #AdobeFirefly will eventually be made up of multiple models, its first model is trained on Adobe Stock, along with openly licensed and public domain content where copyright has expired.

Adobe's profile picture

Adobe

956,428 subscribers

148,446 views • 3 years ago •via X (Twitter)

#AdobeFirefly
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Certified sausage behavior. Made with Adobe by Nobody Sausage.
0:15

Certified sausage behavior. Made with Adobe by Nobody Sausage.

Adobe

65,807 views • 4 months ago

Almost done! Each character comes with 30 animations and is CC0/public domain licensed so they can be added in any of your games or projects! ✨ (Coming... early next week? Probably!)
0:11

Almost done! Each character comes with 30 animations and is CC0/public domain licensed so they can be added in any of your games or projects! ✨ (Coming... early next week? Probably!)

Kenney

18,998 views • 5 months ago

It's sad that this has to be done, but until trained and licensed motorists start acting like adults, it will always be necessary.
0:12

It's sad that this has to be done, but until trained and licensed motorists start acting like adults, it will always be necessary.

Yeah But Cyclists

270,264 views • 5 months ago

Explore the world hiding just outside the boundaries of your photos...✨ with Generative Expand in Adobe Photoshop (beta). Explore this feature and more, now available in 100+ languages:
0:12

Explore the world hiding just outside the boundaries of your photos...✨ with Generative Expand in Adobe Photoshop (beta). Explore this feature and more, now available in 100+ languages:

Adobe

72,617 views • 2 years ago

🚨 Big news: Flux 2 Pro is a new partner model on Adobe Firefly & Photoshop⚡️ What’s special? It’s fast and it’s elite quality. ✅ Better prompt follow-through 🖼️ Up to 4MP images 🌍 Multiple languages support 📌 Multiple reference images ⚙️ Smarter physics Here’s a thread with prompts + where it shines 👇 Bonus news : Unlimited gens until Jan 15 for eligible Firefly Pro/Premium + 7k plans + 5k-credit customers (image models + Firefly Video). This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels
0:10

🚨 Big news: Flux 2 Pro is a new partner model on Adobe Firefly & Photoshop⚡️ What’s special? It’s fast and it’s elite quality. ✅ Better prompt follow-through 🖼️ Up to 4MP images 🌍 Multiple languages support 📌 Multiple reference images ⚙️ Smarter physics Here’s a thread with prompts + where it shines 👇 Bonus news : Unlimited gens until Jan 15 for eligible Firefly Pro/Premium + 7k plans + 5k-credit customers (image models + Firefly Video). This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

Umesh

19,281 views • 5 months ago

Introducing Gemini 3 (with Nano Banana Pro) in Adobe Firefly! Unlock unlimited image generations and endless creative opportunities with Firefly and Creative Cloud Pro plans until Dec 1. Learn more:
0:11

Introducing Gemini 3 (with Nano Banana Pro) in Adobe Firefly! Unlock unlimited image generations and endless creative opportunities with Firefly and Creative Cloud Pro plans until Dec 1. Learn more:

Adobe

43,139 views • 6 months ago

This video combines AI-generated elements (balloon, kite, surfboard, and backgrounds) with my own real-world practical effects and stop motion. I made this for Adobe Firefly and I'll share tutorial tomorrow! Thanks Adobe for sponsoring my art #AdobePartner #AdobeFirefly
0:19

This video combines AI-generated elements (balloon, kite, surfboard, and backgrounds) with my own real-world practical effects and stop motion. I made this for Adobe Firefly and I'll share tutorial tomorrow! Thanks Adobe for sponsoring my art #AdobePartner #AdobeFirefly

Karen X. Cheng

52,250 views • 1 year ago

POV: your job is to keep children safe while crossing the road among trained and licensed motorists ⬇️
0:19

POV: your job is to keep children safe while crossing the road among trained and licensed motorists ⬇️

Yeah But Cyclists

18,499 views • 7 months ago

POV: you're driving along a dual carriageway and a trained and licensed SUV owner decides to ruin your day.
0:11

POV: you're driving along a dual carriageway and a trained and licensed SUV owner decides to ruin your day.

Yeah But Cyclists

394,229 views • 5 months ago

Buzz is high that #K47 is set for a grand release on December 25. With multiple films lined up for the same week, the producer of #45TheMovie has openly said that if Sudeep’s film locks that date, his movie will step aside. #K47RedemptionOnDec25
0:11

Buzz is high that #K47 is set for a grand release on December 25. With multiple films lined up for the same week, the producer of #45TheMovie has openly said that if Sudeep’s film locks that date, his movie will step aside. #K47RedemptionOnDec25

International Khiladi

21,463 views • 9 months ago

There seems to be a large uptick of N Americans going to Xiaohongshu and getting massive culture shock. Will seeing China's public transport content on Xiaohongshu (examples below) change their minds on what is possible with urban public transit and...
0:25

There seems to be a large uptick of N Americans going to Xiaohongshu and getting massive culture shock. Will seeing China's public transport content on Xiaohongshu (examples below) change their minds on what is possible with urban public transit and...

JR Urbane Network

205,484 views • 1 year ago

Eric Pope has confirmed that the March Licensed Chapter will be released on April 2nd. PTB is March 11th.
0:12

Eric Pope has confirmed that the March Licensed Chapter will be released on April 2nd. PTB is March 11th.

Schmuckles

28,843 views • 1 year ago

✨ Adobe Firefly Video Model (beta) is released today!! ✨ It can do really well morphing objects. As Adobe has a lot of materials in its dataset I am impressed with results. if you want to rotate things just add “rotate around” to your prompt #CommunityXAdobe
0:16

✨ Adobe Firefly Video Model (beta) is released today!! ✨ It can do really well morphing objects. As Adobe has a lot of materials in its dataset I am impressed with results. if you want to rotate things just add “rotate around” to your prompt #CommunityXAdobe

Kris Kashtanova

66,019 views • 1 year ago

STARBOY perceives its environment through a camera, microphone, temperature sensor, and accelerometer. We trained multiple tiny image models that run locally on the device, letting it recognize human faces and hand gestures.
0:10

STARBOY perceives its environment through a camera, microphone, temperature sensor, and accelerometer. We trained multiple tiny image models that run locally on the device, letting it recognize human faces and hand gestures.

Daniel Kuntz

114,560 views • 3 months ago

🚨#BREAKING: First ever tornado warning of 2025 has been issued with a confirmed tornado on the ground captured by a fire webcam 📌#Tehama | #California The National Weather Service in California has issued its first tornado warning of 2025 for Tehama County California, where a confirmed tornado was captured live on a fire camera webcam. The tornado was observed touching down and lifting back into the sky multiple times. This warning coincided with a winter storm warning in the area, including the possibility of quarter-sized hail and snow within the tornado warning zone. The warning has since expired.
0:17

🚨#BREAKING: First ever tornado warning of 2025 has been issued with a confirmed tornado on the ground captured by a fire webcam 📌#Tehama | #California The National Weather Service in California has issued its first tornado warning of 2025 for Tehama County California, where a confirmed tornado was captured live on a fire camera webcam. The tornado was observed touching down and lifting back into the sky multiple times. This warning coincided with a winter storm warning in the area, including the possibility of quarter-sized hail and snow within the tornado warning zone. The warning has since expired.

R A W S A L E R T S

555,844 views • 1 year ago

Grok Imagine, the AI video model that doesn't want to be real. Since Grok launched its video capabilities, the discourse has been almost entirely content moderation - what will and won't generate. Spicy mode, regulatory investigations, the EUs reaction. It's loud, it's dramatic. And it's completely missing the point. Because buried underneath all of that noise is something genuinely fascinating for filmmakers and visual creators. Grok Imagine video is the only major AI video model that was built to honor imagination over physics. See how it performs in 6 styles versus other models along with detailed prompts 🧵👇
0:10

Grok Imagine, the AI video model that doesn't want to be real. Since Grok launched its video capabilities, the discourse has been almost entirely content moderation - what will and won't generate. Spicy mode, regulatory investigations, the EUs reaction. It's loud, it's dramatic. And it's completely missing the point. Because buried underneath all of that noise is something genuinely fascinating for filmmakers and visual creators. Grok Imagine video is the only major AI video model that was built to honor imagination over physics. See how it performs in 6 styles versus other models along with detailed prompts 🧵👇

Invideo

1,137,773 views • 2 months ago

Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇
0:10

Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇

Stability AI

150,180 views • 22 days ago

Adobe just added Runway Aleph to its tools! 🎉 Aleph is a powerful AI-driven video editing model. Generate a video and edit it with a prompt You can find Runway Aleph in Adobe Firefly web and Firefly Boards
0:16

Adobe just added Runway Aleph to its tools! 🎉 Aleph is a powerful AI-driven video editing model. Generate a video and edit it with a prompt You can find Runway Aleph in Adobe Firefly web and Firefly Boards

Kris Kashtanova

18,561 views • 5 months ago

hi all, excited to join! i'm building an expressive mini "shoggoth" robot which will eventually be hooked up to gpt4o realtime voice. i'm currently working on the low-level policies, which are trained in a mujoco simulation with RL. to delay working on raw-pixels for now, i trained a pose-estimation model using deeplabcut and triangulate the position in 3d space using the stereo cameras. eventually, i'll use gpt4o's tool calling capabilities to activate several of these policies (closed and open loop) based on the dialog flow! captions: manual actuation of the tentacle / 3d pose estimation / target design
0:29

hi all, excited to join! i'm building an expressive mini "shoggoth" robot which will eventually be hooked up to gpt4o realtime voice. i'm currently working on the low-level policies, which are trained in a mujoco simulation with RL. to delay working on raw-pixels for now, i trained a pose-estimation model using deeplabcut and triangulate the position in 3d space using the stereo cameras. eventually, i'll use gpt4o's tool calling capabilities to activate several of these policies (closed and open loop) based on the dialog flow! captions: manual actuation of the tentacle / 3d pose estimation / target design

Matthieu LC

45,506 views • 1 year ago