Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Timelapse of using #photoshop’s new generative fill feature to connect two images and build a scene around them using blank prompts. Was inspired by MatthieuGB’s post doing something similar! Notice how I’m not adding any descriptions, but letting gen fill present options for extending the current selection as I... show more

CoffeeVectors

42,894 subscribers

1,725,839 просмотров • 3 лет назад •via X (Twitter)

Образование Наука и технологии Искусство #photoshop

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля CoffeeVectors

CoffeeVectors3 лет назад

Here’s the final image! 2/4

Фото профиля CoffeeVectors

CoffeeVectors3 лет назад

And here are the original images made in #midjourneyv51 3/4

Фото профиля CoffeeVectors

CoffeeVectors3 лет назад

And this is @MatthieuGB’s original post that inspired me to use blank prompts to join images together! Check out his stuff and give him a follow! 4/4

Фото профиля Steve Mills

Steve Mills3 лет назад

@MatthieuGB What a fantastic idea, I never thought to just let it fill the gaps between two similar styled generations. The innovative workflows that people are coming up with are outstanding. The tools are pushed to areas that the creators had no idea was possible.

Фото профиля CoffeeVectors

CoffeeVectors3 лет назад

@MatthieuGB It was something ppl were doing with Dall-E 2 last year, but blank prompts is something that surprised me!

Фото профиля accel_agi

accel_agi3 лет назад

@MatthieuGB This reminds me of InvokeAI. Nice that photoshop is doing generative ai stiff.

Фото профиля EyeSeeThru 👁️

EyeSeeThru 👁️3 лет назад

@MatthieuGB Awesomeness!

Фото профиля CoffeeVectors

CoffeeVectors3 лет назад

@MatthieuGB Thank you!!

Фото профиля Junior Ferpazzi

Junior Ferpazzi3 лет назад

@MatthieuGB 🤘😎

Фото профиля Mrboofy

Mrboofy3 лет назад

@MatthieuGB This is spectacular 🙀

Фото профиля CoffeeVectors

CoffeeVectors3 лет назад

@MatthieuGB Thank you! Very exciting stuff!

Похожие видео

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Martin Nebelong

280,078 просмотров • 1 год назад

I dont know why Content Fill AI for video was not available in Adobe suite. So I made it as a plugin and it’s open-source for After effects!! Super easy Installation in two click for Mac and PC, it’s using fal .ai api for the generation. Two mods are possible : - Content fill from mask using Wan 2.1 ( more precise ! ) - Content fill from prompt using Wan 2.2 ( less precise, better quality!) It’s still a prototype and it’s possible that you encounter some bug, that is why I also made it open for now. But could be cool to develop that with much more functionalities ! For automatic download of the final file it’s working good on Mac, but on Pc it will show a popup to download it manually.

I dont know why Content Fill AI for video was not available in Adobe suite. So I made it as a plugin and it’s open-source for After effects!! Super easy Installation in two click for Mac and PC, it’s using fal .ai api for the generation. Two mods are possible : - Content fill from mask using Wan 2.1 ( more precise ! ) - Content fill from prompt using Wan 2.2 ( less precise, better quality!) It’s still a prototype and it’s possible that you encounter some bug, that is why I also made it open for now. But could be cool to develop that with much more functionalities ! For automatic download of the final file it’s working good on Mac, but on Pc it will show a popup to download it manually.

Lovis Odin

19,763 просмотров • 1 год назад

Using Nano Banana Pro + Sora, I can now create a short video in just about one minute. I’ve been using Kling for a while to make short videos, and while the results can be great, the workflow has always felt a bit heavy for me. Previously, I had to export the video frame by frame as images, then send those keyframes into Kling’s first/last frame mode to generate the in-betweens. It worked, but it took a lot of time and small steps. Recently I realized I don’t necessarily need to do that anymore: now I can use Nano Banana Pro to generate the images, then send them directly to Sora to create the short video—no need to manually extract a specific frame. Another bonus is that Sora also handles basic sound design for you, which saves me from an extra round of editing and makes the whole process feel much lighter. This idea actually came from a post I saw this morning on Twitter by SD | AI Animation Storyteller, which gave me a new way of thinking about my workflow. I’m still experimenting, but so far it’s been a big improvement in efficiency for my use case. I’ve put the detailed steps I’m using in the comments in case anyone wants to try something similar.

Using Nano Banana Pro + Sora, I can now create a short video in just about one minute. I’ve been using Kling for a while to make short videos, and while the results can be great, the workflow has always felt a bit heavy for me. Previously, I had to export the video frame by frame as images, then send those keyframes into Kling’s first/last frame mode to generate the in-betweens. It worked, but it took a lot of time and small steps. Recently I realized I don’t necessarily need to do that anymore: now I can use Nano Banana Pro to generate the images, then send them directly to Sora to create the short video—no need to manually extract a specific frame. Another bonus is that Sora also handles basic sound design for you, which saves me from an extra round of editing and makes the whole process feel much lighter. This idea actually came from a post I saw this morning on Twitter by SD | AI Animation Storyteller, which gave me a new way of thinking about my workflow. I’m still experimenting, but so far it’s been a big improvement in efficiency for my use case. I’ve put the detailed steps I’m using in the comments in case anyone wants to try something similar.

underwood

46,400 просмотров • 9 месяцев назад

I finally spent some time with Alibaba Cloud for video and the results are really fun. I started by using some images I generated right on the same site as references for a cooking animation. The stability was the best part. I did not see any of the usual glitching with ingredients doubling up. Everything looked solid, especially the water physics and how the steam reacted to the heat.

I finally spent some time with Alibaba Cloud for video and the results are really fun. I started by using some images I generated right on the same site as references for a cooking animation. The stability was the best part. I did not see any of the usual glitching with ingredients doubling up. Everything looked solid, especially the water physics and how the steam reacted to the heat.

Chubby♨️

20,686 просмотров • 3 месяцев назад

BUZZ 🐝 A short sequence created using Nano Banana Pro and Grok imagine. I wanted to test Groks capabilities for action in motion. With Buzz leading the way, Tiny Timmy is having the absolute time of his life exploring the wondrous Flower Kingdom🌼 Tools for creation: - Nano Banana Pro was used to generate the base image and the additional camera angles. I wanted to personally see if I could just use 3 images so no 2x2 grid extraction technique for this but I did want to include each frame used so you can see how the sequence was combined. Grok Imagine was used for every sequence to bring it to life using image to video. - I did some post work in Capcut by adding some subtle bloom, radial motion blur and film grain as well. - I added additional sound effects by generating them using Elevenlabs and layering them (bee buzzing, flapping wings, wind and leaves rustling etc). The kids laughter was generated using Grok. The soundtrack was sourced from Artlist. It was fun testing this and putting it together just to see what Grok is capable of generating.

BUZZ 🐝 A short sequence created using Nano Banana Pro and Grok imagine. I wanted to test Groks capabilities for action in motion. With Buzz leading the way, Tiny Timmy is having the absolute time of his life exploring the wondrous Flower Kingdom🌼 Tools for creation: - Nano Banana Pro was used to generate the base image and the additional camera angles. I wanted to personally see if I could just use 3 images so no 2x2 grid extraction technique for this but I did want to include each frame used so you can see how the sequence was combined. Grok Imagine was used for every sequence to bring it to life using image to video. - I did some post work in Capcut by adding some subtle bloom, radial motion blur and film grain as well. - I added additional sound effects by generating them using Elevenlabs and layering them (bee buzzing, flapping wings, wind and leaves rustling etc). The kids laughter was generated using Grok. The soundtrack was sourced from Artlist. It was fun testing this and putting it together just to see what Grok is capable of generating.

Travis Davids

14,990 просмотров • 7 месяцев назад

brain rotting, but the thoughts still racing // Testing img2vid lipsyncing with the InfiniteTalk model on WaveSpeedAI and a song I made in Suno v5. Love how it handles images with multiple faces and how it animates even when it doesn’t see a mouth. Quick tutorial in 🧵👇 (1/6)

brain rotting, but the thoughts still racing // Testing img2vid lipsyncing with the InfiniteTalk model on WaveSpeedAI and a song I made in Suno v5. Love how it handles images with multiple faces and how it animates even when it doesn’t see a mouth. Quick tutorial in 🧵👇 (1/6)

CoffeeVectors

29,987 просмотров • 9 месяцев назад

Here's how we made a 1-minute sequence of "The long road back". An animation short-film we've done at Magnific Studios. The process was roughly: - We started with reference images of the boy (Nilo), dog (Pip), the witch and witch house. Krea 2 image model, Nana Banana Pro were heavily used in reference image generation. - The video model was Seedance 2 generations. 15 seconds and with prompts asking for different shots. We basically prompted for 'scenes' - not shots. Trying to generate stand-alone shots and then editing together gives too many problems with continuity. - For every additional 15 second video (we needed at least 4), we would provide the last 5 seconds of the previous video as reference to Seedance 2 + the original reference images. Then in the prompt, ask for continuing the video + prompting for the next part of the story. This proved very productive. - We fixed inconsistencies in many shots by surgically extract the few problematic sections. Then edit 1 frame using Nano Banana. And then regenerating the sequences using this new reference image and Seedance 2. Two examples. The doorknob changed place and the door behind the dog was closed even after the witch stepped out. - All music was generated using Elevenlabs music generator. 3 seperate pieces of music. - All editing and color grading was done in Davinci Resolve. Everything gen AI above was done using Magnific

Here's how we made a 1-minute sequence of "The long road back". An animation short-film we've done at Magnific Studios. The process was roughly: - We started with reference images of the boy (Nilo), dog (Pip), the witch and witch house. Krea 2 image model, Nana Banana Pro were heavily used in reference image generation. - The video model was Seedance 2 generations. 15 seconds and with prompts asking for different shots. We basically prompted for 'scenes' - not shots. Trying to generate stand-alone shots and then editing together gives too many problems with continuity. - For every additional 15 second video (we needed at least 4), we would provide the last 5 seconds of the previous video as reference to Seedance 2 + the original reference images. Then in the prompt, ask for continuing the video + prompting for the next part of the story. This proved very productive. - We fixed inconsistencies in many shots by surgically extract the few problematic sections. Then edit 1 frame using Nano Banana. And then regenerating the sequences using this new reference image and Seedance 2. Two examples. The doorknob changed place and the door behind the dog was closed even after the witch stepped out. - All music was generated using Elevenlabs music generator. 3 seperate pieces of music. - All editing and color grading was done in Davinci Resolve. Everything gen AI above was done using Magnific

Martin LeBlanc

25,384 просмотров • 2 месяцев назад

Being an Adobe Firefly Ambassador is such a rewarding experience. I’m truly grateful to be one of the many creators in this amazing program. I’ve been sharing AI art since 2023, and when Adobe invited me to become a Firefly Ambassador, I was so excited. Huge thanks to Kris for recommending me! Getting access to Adobe’s ecosystem, Firefly, and all their generative AI tools is incredible. But what makes it even better is the community , a group of talented people who constantly inspire each other and share knowledge. Creating something new is already rewarding, and being able to do it as part of a paid opportunity makes it even more special. The journey has been amazing so far. Join us and learn more about the program ⤵️ This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeAmbassadors #Ad #MyAdobeAmbassadorStory

Being an Adobe Firefly Ambassador is such a rewarding experience. I’m truly grateful to be one of the many creators in this amazing program. I’ve been sharing AI art since 2023, and when Adobe invited me to become a Firefly Ambassador, I was so excited. Huge thanks to Kris for recommending me! Getting access to Adobe’s ecosystem, Firefly, and all their generative AI tools is incredible. But what makes it even better is the community , a group of talented people who constantly inspire each other and share knowledge. Creating something new is already rewarding, and being able to do it as part of a paid opportunity makes it even more special. The journey has been amazing so far. Join us and learn more about the program ⤵️ This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeAmbassadors #Ad #MyAdobeAmbassadorStory

Umesh

11,968 просмотров • 6 месяцев назад

Our very own Alexander Chen created "Hello, world" a short film inspired by the technology of his childhood with Google Labs Flow. Here's a closer look at how he brought his vision to life: 1) All of the clips were generated in Flow using text-to-image prompts except he used image-to-video prompts for the close-up shots to ensure consistency and accuracy (and the images used were generated by Imagen). 2) To evoke the exact feelings of his childhood home, he used Google Street View for visual references then asked the Google Gemini to write descriptions and prompts, then uploaded those into Flow which is what produced such vivid and accurate renderings in the film. 3) Every sound used in the video is generated by Veo 3. However, to blend things together, he used a separate video editing software to extend the head and tail of each clip over the proceeding and following clip, occasionally crossfading the audio to help with transitions.

Our very own Alexander Chen created "Hello, world" a short film inspired by the technology of his childhood with Google Labs Flow. Here's a closer look at how he brought his vision to life: 1) All of the clips were generated in Flow using text-to-image prompts except he used image-to-video prompts for the close-up shots to ensure consistency and accuracy (and the images used were generated by Imagen). 2) To evoke the exact feelings of his childhood home, he used Google Street View for visual references then asked the Google Gemini to write descriptions and prompts, then uploaded those into Flow which is what produced such vivid and accurate renderings in the film. 3) Every sound used in the video is generated by Veo 3. However, to blend things together, he used a separate video editing software to extend the head and tail of each clip over the proceeding and following clip, occasionally crossfading the audio to help with transitions.

Google AI

94,790 просмотров • 1 год назад

“Passion was one of the most important records for me – an opportunity as a writer to try to do a different sort of job than I usually do. The brief for ‘The Last Temptation Of Christ’ was to create something that had references to that time and that part of the world, but that had its own character and was to be timeless in a way.” - PG. This track ‘Zaar’ was written around a traditional Egyptian rhythm which is performed to fend off evil spirits. The video was directed by Stefan Roloff using images from his film ‘Lunch’.

“Passion was one of the most important records for me – an opportunity as a writer to try to do a different sort of job than I usually do. The brief for ‘The Last Temptation Of Christ’ was to create something that had references to that time and that part of the world, but that had its own character and was to be timeless in a way.” - PG. This track ‘Zaar’ was written around a traditional Egyptian rhythm which is performed to fend off evil spirits. The video was directed by Stefan Roloff using images from his film ‘Lunch’.

Peter Gabriel

37,343 просмотров • 2 лет назад

I tested out Cyberpunk 2077 Path Tracing turned on with RX 9070 XT now that FSR Redstone is out. By using the new FSR Redstone and FSR ML Based Frame-Gen, the game reaches up to 130FPS in 1440p with FSR set to Performance Mode. The performance gains are not that much higher compared to the previous versions of FSR but the image quality got a huge upgrade, especially when using Frame-Gen. This ML based Frame Gen is much better than the previous version as it gets rid of most artifacts and ghosting caused by the previous version. If for some reason you always wanted to play Cyberpunk 2077 with Path Tracing turned on on an AMD GPU, now you can enjoy a playable experience with 100+ FPS on an RX 9070 XT. I still don't recommend it though as the frame pacing and input lag still feels off for me, I'd just rather play this without Frame Gen and Path Tracing. I'm going to test out Black Myth: Wukong next

I tested out Cyberpunk 2077 Path Tracing turned on with RX 9070 XT now that FSR Redstone is out. By using the new FSR Redstone and FSR ML Based Frame-Gen, the game reaches up to 130FPS in 1440p with FSR set to Performance Mode. The performance gains are not that much higher compared to the previous versions of FSR but the image quality got a huge upgrade, especially when using Frame-Gen. This ML based Frame Gen is much better than the previous version as it gets rid of most artifacts and ghosting caused by the previous version. If for some reason you always wanted to play Cyberpunk 2077 with Path Tracing turned on on an AMD GPU, now you can enjoy a playable experience with 100+ FPS on an RX 9070 XT. I still don't recommend it though as the frame pacing and input lag still feels off for me, I'd just rather play this without Frame Gen and Path Tracing. I'm going to test out Black Myth: Wukong next

NikTek

242,749 просмотров • 8 месяцев назад

Took a simple fluid sim scene that I set up in Blender using a python script made in o3-mini. And then I ran it through several styles with vid2vid in Runway 🧵1/5

Took a simple fluid sim scene that I set up in Blender using a python script made in o3-mini. And then I ran it through several styles with vid2vid in Runway 🧵1/5

CoffeeVectors

18,739 просмотров • 1 год назад

Make Art Not War: The Battle for Creativity It's Adobe's annual Max event in London today and scott belsky's spotlight on AI paints a clear picture: AI isn't just on Adobe's agenda, it is the agenda. Adobe has already scored a home run with generative fill in Photoshop, a feature now spawning entire categories of memes - including my own video, which surprisingly garnered a million views. However, Adobe's ambitions extend beyond still imagery. The Tanker Charges Towards Video At Max, Adobe's Chief Product Officer put an emphasis on AI video generation with Firefly Video. The tech tanker is charging full steam ahead to the next obvious modality for creation, leaving a wake of disruption for any upstarts bold enough to challenge it. The announcement isn't new, but it showcases the emphasis on new product development with a marked increase in the velocity we can expect from the creative tech behemoth. The company that defined the norms of video editing with Premiere, and motion graphics with After Effects, has now entered the realm of AI-powered creation. The wake-up call is clear - the tankers are moving fast. Goliath vs. The Upstarts This development spells a daunting challenge for the numerous start-ups that dared to dethrone Adobe in recent years. For plenty of use cases people have been asking: Why use Photoshop when you have MidJourney? Why use Premiere when you have Descript? Why use After Effects when you have Runway? These aspiring disruptors sought to chip away at Adobe's dominance by offering more specialized, user-friendly solutions - a process that can be characterized as the 'unbundling' of Adobe. Now, they face a head-to-head collision with the very Goliath they sought to topple. Creators' Toolkit: A New Addition But this imminent clash isn't just a tale of corporate competition. This is a story about the tools of creation and their impact on creators themselves and the very canvas of creation. The advent of Firefly, Adobe's AI-driven offering, reflects a broadening recognition of artificial intelligence as an integral part of the creator's toolkit. In other words, Adobe's massive ecosystem of creators needn't wade out into new waters to acquire AI capabilities -- they will simply be infused into the products they already know and (mostly) love, but more critically -- need to use every day to get creative stuff done. The Increasing Stickiness of Adobe's Tools The intersection of AI and creative tools like Photoshop's generative fill is transforming how creators perceive and interact with AI. When they encounter the innovative features of generative fill, they're not primarily thinking about the AI technology that powers it. Instead, they're marveling at the cool new tool that's now part of their beloved Photoshop. This immediate affinity for "Photoshop" masks the sophisticated technology behind it, essentially furthering Adobe's stronghold on the creative industry. Layer in Adobe's stance to training their AI models with sources like Adobe Stock that promise rock-solid data provenance, and you can see Adobe clearly wants to seem like the responsible adults in the room. After all Adobe elected not to put the Behance catalog to work, perhaps rightly so given the ethical backlash to the scraping Artstation imagery. Adobe's Thirty Something Conundrum But it's not all rainbows and sunshine. While Adobe sails ahead full steam, there's an intriguing conundrum waiting in the wings. With 30-year-old codebases forming the foundation of its most popular tools, Adobe faces a significant challenge: its software has back pain. But it's not just a technical problem -- it's also a philosophical one, akin to the ship of Theseus. Can Adobe modernize and refactor its code bases without sacrificing the essence that made these tools indispensable to creators? Can they innovate without alienating their long-time users who've grown accustomed to the 'Adobe way' of doing things? An Unexpected Solution? Interestingly, solutions might emerge from unexpected quarters. Perhaps it'll take an army of developers armed with GitHub Co-Pilot to alleviate Adobe's refactoring nightmare. By automating parts of the refactoring process, it could accelerate the evolution of Adobe's legacy tools, making them more adaptable to the rapidly progressing tech landscape while preserving their core functionality. In a twist of irony, the AI that's reshaping Adobe's offerings might just come to the rescue of its own legacy. As Adobe navigates these murky waters, opportunities are emerging for new entrants in the field. Startups might also find their moment to shine in the midst of Adobe's strategic and technological shifts. With their innovative approaches and less-encumbered platforms, they have the chance to offer alternative solutions to creators seeking novel, efficient, and intuitive tools. The Battle for Creativity The tech giant's journey through a massive transformation at a previously unfathomable speed will set the course for the next era of creative technology. Given the sheer ubiquity of Adobe tools today, it's by far the most common way creators will experience AI. But let's be honest -- this transformation will not be easy. The future of creative tech isn't written yet and as a growing line up of new entrants vie for the prize, one thing's for sure: it's going to be a darn good fight. Make Art Not War In the end, it is the creators who stand to gain the most. As Adobe and its competitors lock horns, they'll strive to deliver increasingly powerful, intuitive, and efficient tools. But, it's up to the creators themselves to harness these innovations. Only by embracing and mastering these new tools can they unlock their full creative potential. So what are you waiting for? Wield these new tools at your disposal and turn your imagination into reality. We are the architects of a new era of creative self expression. If you enjoyed this, drop a like and retweet. Follow Bilawal Sidhu for more writing on creative tech and AI.

Make Art Not War: The Battle for Creativity It's Adobe's annual Max event in London today and scott belsky's spotlight on AI paints a clear picture: AI isn't just on Adobe's agenda, it is the agenda. Adobe has already scored a home run with generative fill in Photoshop, a feature now spawning entire categories of memes - including my own video, which surprisingly garnered a million views. However, Adobe's ambitions extend beyond still imagery. The Tanker Charges Towards Video At Max, Adobe's Chief Product Officer put an emphasis on AI video generation with Firefly Video. The tech tanker is charging full steam ahead to the next obvious modality for creation, leaving a wake of disruption for any upstarts bold enough to challenge it. The announcement isn't new, but it showcases the emphasis on new product development with a marked increase in the velocity we can expect from the creative tech behemoth. The company that defined the norms of video editing with Premiere, and motion graphics with After Effects, has now entered the realm of AI-powered creation. The wake-up call is clear - the tankers are moving fast. Goliath vs. The Upstarts This development spells a daunting challenge for the numerous start-ups that dared to dethrone Adobe in recent years. For plenty of use cases people have been asking: Why use Photoshop when you have MidJourney? Why use Premiere when you have Descript? Why use After Effects when you have Runway? These aspiring disruptors sought to chip away at Adobe's dominance by offering more specialized, user-friendly solutions - a process that can be characterized as the 'unbundling' of Adobe. Now, they face a head-to-head collision with the very Goliath they sought to topple. Creators' Toolkit: A New Addition But this imminent clash isn't just a tale of corporate competition. This is a story about the tools of creation and their impact on creators themselves and the very canvas of creation. The advent of Firefly, Adobe's AI-driven offering, reflects a broadening recognition of artificial intelligence as an integral part of the creator's toolkit. In other words, Adobe's massive ecosystem of creators needn't wade out into new waters to acquire AI capabilities -- they will simply be infused into the products they already know and (mostly) love, but more critically -- need to use every day to get creative stuff done. The Increasing Stickiness of Adobe's Tools The intersection of AI and creative tools like Photoshop's generative fill is transforming how creators perceive and interact with AI. When they encounter the innovative features of generative fill, they're not primarily thinking about the AI technology that powers it. Instead, they're marveling at the cool new tool that's now part of their beloved Photoshop. This immediate affinity for "Photoshop" masks the sophisticated technology behind it, essentially furthering Adobe's stronghold on the creative industry. Layer in Adobe's stance to training their AI models with sources like Adobe Stock that promise rock-solid data provenance, and you can see Adobe clearly wants to seem like the responsible adults in the room. After all Adobe elected not to put the Behance catalog to work, perhaps rightly so given the ethical backlash to the scraping Artstation imagery. Adobe's Thirty Something Conundrum But it's not all rainbows and sunshine. While Adobe sails ahead full steam, there's an intriguing conundrum waiting in the wings. With 30-year-old codebases forming the foundation of its most popular tools, Adobe faces a significant challenge: its software has back pain. But it's not just a technical problem -- it's also a philosophical one, akin to the ship of Theseus. Can Adobe modernize and refactor its code bases without sacrificing the essence that made these tools indispensable to creators? Can they innovate without alienating their long-time users who've grown accustomed to the 'Adobe way' of doing things? An Unexpected Solution? Interestingly, solutions might emerge from unexpected quarters. Perhaps it'll take an army of developers armed with GitHub Co-Pilot to alleviate Adobe's refactoring nightmare. By automating parts of the refactoring process, it could accelerate the evolution of Adobe's legacy tools, making them more adaptable to the rapidly progressing tech landscape while preserving their core functionality. In a twist of irony, the AI that's reshaping Adobe's offerings might just come to the rescue of its own legacy. As Adobe navigates these murky waters, opportunities are emerging for new entrants in the field. Startups might also find their moment to shine in the midst of Adobe's strategic and technological shifts. With their innovative approaches and less-encumbered platforms, they have the chance to offer alternative solutions to creators seeking novel, efficient, and intuitive tools. The Battle for Creativity The tech giant's journey through a massive transformation at a previously unfathomable speed will set the course for the next era of creative technology. Given the sheer ubiquity of Adobe tools today, it's by far the most common way creators will experience AI. But let's be honest -- this transformation will not be easy. The future of creative tech isn't written yet and as a growing line up of new entrants vie for the prize, one thing's for sure: it's going to be a darn good fight. Make Art Not War In the end, it is the creators who stand to gain the most. As Adobe and its competitors lock horns, they'll strive to deliver increasingly powerful, intuitive, and efficient tools. But, it's up to the creators themselves to harness these innovations. Only by embracing and mastering these new tools can they unlock their full creative potential. So what are you waiting for? Wield these new tools at your disposal and turn your imagination into reality. We are the architects of a new era of creative self expression. If you enjoyed this, drop a like and retweet. Follow Bilawal Sidhu for more writing on creative tech and AI.

Bilawal Sidhu

72,192 просмотров • 3 лет назад

More Wan 2.2 tests on Here I wanted to compare it directly to Veo 3 and also see how tight into the eye I could get with complex zooms. Again I’m really surprised by what Wan 2.2 can do. The prompts are the same across models, so Wan seems to be able to do more with the text, at least with camera moves and optics. 🧵

More Wan 2.2 tests on Here I wanted to compare it directly to Veo 3 and also see how tight into the eye I could get with complex zooms. Again I’m really surprised by what Wan 2.2 can do. The prompts are the same across models, so Wan seems to be able to do more with the text, at least with camera moves and optics. 🧵

CoffeeVectors

60,769 просмотров • 1 год назад

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,841 просмотров • 11 месяцев назад

I'm proud to present this video created with Grok. Here are the main steps in the making of this video: 1. I wrote a draft script by hand. 2. I reworked the script with Grok to eliminate inconsistencies and add technical details (what I have them say about the Apollo missions and the stones is accurate). 3. Grok broke it down into scenes. 4. I switched to Grok Imagine's Agent mode: transforming each scene into a prompt. 5. I animated each scene in Agent mode using video, as well as cropping and image selection. 6. I edited it. Here's the result; it's hard to call it AI. I look forward to reading your comments. Grok Imagine Elon Musk

I'm proud to present this video created with Grok. Here are the main steps in the making of this video: 1. I wrote a draft script by hand. 2. I reworked the script with Grok to eliminate inconsistencies and add technical details (what I have them say about the Apollo missions and the stones is accurate). 3. Grok broke it down into scenes. 4. I switched to Grok Imagine's Agent mode: transforming each scene into a prompt. 5. I animated each scene in Agent mode using video, as well as cropping and image selection. 6. I edited it. Here's the result; it's hard to call it AI. I look forward to reading your comments. Grok Imagine Elon Musk

Déborah

69,706 просмотров • 2 месяцев назад

Made this video with iPhone photos I took of my friend Stephanie that I used as keyframes in Luma! With the camera controls I can gen transitions between shots. I also built a custom web app in Next.js to help me speedramp and edit all the clips! Breakdown 🧵(1/18)

Made this video with iPhone photos I took of my friend Stephanie that I used as keyframes in Luma! With the camera controls I can gen transitions between shots. I also built a custom web app in Next.js to help me speedramp and edit all the clips! Breakdown 🧵(1/18)

CoffeeVectors

338,601 просмотров • 1 год назад

🎓Learn how to create a powerful Worn Leather smart material in a matter of seconds in my latest video series (AAA) Pro Tips! This smart material can be used on virtually any 3D asset. ____________________________________________________ In this video, the steps are as follows: 1. Create a fill layer with a black mask applied. Inside its mask paint a simple pill shape and use a blur slope filter to introduce some random shapes. Apply a marble veins fill layer on top with its blending mode set to color burn. Apply a warp filter as well to introduce some randomness followed by an anchorpoint. 2. Create another fill layer using the same technique to apply some dirt in the crevices of the wear. 3. Next, Inside the main fill layer apply a tiling raw leather texture to its Color and roughness channel 4. Create an additional fill layer up top and apply a black mask to it.Inside this mask retrieve the anchorpoint information followed by a blur filter with a value of 6. Use a levels to increase the spread of the mask. Apply another marble veins matching the values of the marble veins fill layer that we previously added and set its blending mode to multiply. Lastly retrieve the anchorpoint information from the previous fill layer again but this time set its blending mode to subtract. This fill layers properties should have a dark diffuse color and a matte roughness. 5. Add another fill layer with a bright diffuse and height properties with a black mask applied to it. Inside its mask retrieve the anchorpoint information again followed by a blur slope. Apply the anchorpoint information again but this time set its blending mode to subtract. Now we have a worn leather effect wherever we paint using the paint layer created inside the callout mask! ____________________________________________________ More AAA Game Dev Tips can be found on my YouTube channel here: Stay tuned for more weekly Tips! Happy Texturing!💚 #gamedev #gameart #3dmodeling #3dartist #texturing #UE5 #unity #artstation

🎓Learn how to create a powerful Worn Leather smart material in a matter of seconds in my latest video series (AAA) Pro Tips! This smart material can be used on virtually any 3D asset. In this video, the steps are as follows: 1. Create a fill layer with a black mask applied. Inside its mask paint a simple pill shape and use a blur slope filter to introduce some random shapes. Apply a marble veins fill layer on top with its blending mode set to color burn. Apply a warp filter as well to introduce some randomness followed by an anchorpoint. 2. Create another fill layer using the same technique to apply some dirt in the crevices of the wear. 3. Next, Inside the main fill layer apply a tiling raw leather texture to its Color and roughness channel 4. Create an additional fill layer up top and apply a black mask to it.Inside this mask retrieve the anchorpoint information followed by a blur filter with a value of 6. Use a levels to increase the spread of the mask. Apply another marble veins matching the values of the marble veins fill layer that we previously added and set its blending mode to multiply. Lastly retrieve the anchorpoint information from the previous fill layer again but this time set its blending mode to subtract. This fill layers properties should have a dark diffuse color and a matte roughness. 5. Add another fill layer with a bright diffuse and height properties with a black mask applied to it. Inside its mask retrieve the anchorpoint information again followed by a blur slope. Apply the anchorpoint information again but this time set its blending mode to subtract. Now we have a worn leather effect wherever we paint using the paint layer created inside the callout mask! More AAA Game Dev Tips can be found on my YouTube channel here: Stay tuned for more weekly Tips! Happy Texturing!💚 #gamedev #gameart #3dmodeling #3dartist #texturing #UE5 #unity #artstation

Cohen Brawley

88,726 просмотров • 2 лет назад