ChatGPT 14:42 🧠 The discussion on using ChatGPT for prompt generation and storytelling begins. 36:07 💡 They explore ChatGPT's vision feature and its applications in creative tasks. Runway 37:09 🎥 Introduction to Runway's AI video generation capabilities. 38:07 🎬 Discussion on how Runway is used with Midjourney for animating images. Krea 48:50 🔍 The introduction of Krea as a tool for image upscaling and enhancement. 51:13 🖌 Discussion on Krea's capabilities in restoring low-resolution images and adding details. Magnific 57:15 🎨 Introduction to Magnific and its effectiveness in image upscaling. 58:52 🍔 Discussion on how Magnific enhances image textures and details. Adobe (Photoshop and Illustrator) 01:03:19 🎨 Adobe Photoshop's generative fill and other features are highlighted. 01:09:06 👕 Discussion on Adobe Illustrator's mockup generator and other creative tools.
@@MidjourneyFastHours check out the "Harpa AI" browser extension. It's MASSIVELY helpful with everyday tasks. (That's what I used to summarize the video transcript, and add timestamps), but it has MANY more uses also. 😎
I have an idea for an option within Repainting that I think would be extremely useful. Mirror symmetry is what I describe it as. Select the area you want changed, select mirror symmetry, have an exact same size area pop up (like using Clone in Lightroom) but flipped, drag it over the area that you want to mirror and then voila, MJ repaints it. I'd love to see light room include the same option with Clone where you could flip the selected area and mirror another area of the pic to get that perfect symmetry. What do you think? I'd love for MJ to consider the idea.
Thank you all very much for your great contribution. I love your new project here on UA-cam and can hardly wait to see the next episode. I have a small tip here that is quite specific but could also be interesting for you. It’s an AI tool specifically designed to swap faces on real photos. This is particularly useful for clients who have issues with model releases. The tool is called Erase ID. As a case example, I can mention an internationally operating client who organized a photo shoot for a brochure a while back. Now, this brochure needs to be adapted for the global market, which means that, for example, the European faces are not suitable for the Asian market. I used this tool to swap the faces and can specify ethnicity, as well as many other aspects such as facial expressions, hairstyles, facial hair, etc. It’s also possible to apply masks. This works quite well and is an extremely financially interesting alternative for the client to address this problem. The alternative would be a completely new photo shoot with ethnically adjusted models, which of course would not be cost-effective. I am neither affiliated with this company nor do I benefit from promoting it, but if you're interested, you might want to check it out.
Midjourney seems a strange choice for consistency when there are powerful independent workflows specifically designed for the commercial world using models and powerful structuring software. I like both but certainly couldn’t use Midjourney in terms of its propensity to hallucinate and fail with key details in so much of its output. Runway is very easy to use and the output is getting much better it’s expensive like Magnific so it can be a costly learning process but very enjoyable. Krea needs to introduce privacy modes before being a consideration.
Great video. Got through 2/3 and had to hit that subscribe button so I won’t miss another one. Not sure if you’ve covered it but the censor in MJ is an issue, so is there a tip to have a work around, such as a suggestion of what is acceptable or find out why it’s not accepted?
nice:) i like gen3 + midjourney workflow - but you need unlimited subscriptions - to achive great results you need a lot o generations. Leonardo AI has a good upscaler + Kling AI - gives me better human animation than gen3. For prompting I like claude 3.5 - instaed GPT4o.
Great episode. Love what you guys are doing. Thanks for sharing your knowledge.
@@ChrisElmbank appreciate the support!
ChatGPT
14:42 🧠 The discussion on using ChatGPT for prompt generation and storytelling begins.
36:07 💡 They explore ChatGPT's vision feature and its applications in creative tasks.
Runway
37:09 🎥 Introduction to Runway's AI video generation capabilities.
38:07 🎬 Discussion on how Runway is used with Midjourney for animating images.
Krea
48:50 🔍 The introduction of Krea as a tool for image upscaling and enhancement.
51:13 🖌 Discussion on Krea's capabilities in restoring low-resolution images and adding details.
Magnific
57:15 🎨 Introduction to Magnific and its effectiveness in image upscaling.
58:52 🍔 Discussion on how Magnific enhances image textures and details.
Adobe (Photoshop and Illustrator)
01:03:19 🎨 Adobe Photoshop's generative fill and other features are highlighted.
01:09:06 👕 Discussion on Adobe Illustrator's mockup generator and other creative tools.
Want to do future notes for us?! 😂
@@MidjourneyFastHours check out the "Harpa AI" browser extension. It's MASSIVELY helpful with everyday tasks. (That's what I used to summarize the video transcript, and add timestamps), but it has MANY more uses also. 😎
I appreciate these AI therapy sessions
It’s cathartic and keeps us all sane.
you can remove blemishes etc and upscale with ON1. I use that and the Affinity tools for design stuff.
Any chance you can share the ChatGPT "Describe" tool you've created...?? (Great episode, btw!)
Absolutely.
Here's the link: chatgpt.com/g/g-KkEHrDNbM-describe
-DB
Just started using Runway over the weekend (thanks Rory). Still can’t believe I can turn my Midjourney images into a video 🤯
You can fly through those gens faaaaast. Have fun!
-DB
I have an idea for an option within Repainting that I think would be extremely useful. Mirror symmetry is what I describe it as. Select the area you want changed, select mirror symmetry, have an exact same size area pop up (like using Clone in Lightroom) but flipped, drag it over the area that you want to mirror and then voila, MJ repaints it. I'd love to see light room include the same option with Clone where you could flip the selected area and mirror another area of the pic to get that perfect symmetry. What do you think? I'd love for MJ to consider the idea.
Thank you all very much for your great contribution. I love your new project here on UA-cam and can hardly wait to see the next episode. I have a small tip here that is quite specific but could also be interesting for you. It’s an AI tool specifically designed to swap faces on real photos. This is particularly useful for clients who have issues with model releases. The tool is called Erase ID. As a case example, I can mention an internationally operating client who organized a photo shoot for a brochure a while back. Now, this brochure needs to be adapted for the global market, which means that, for example, the European faces are not suitable for the Asian market. I used this tool to swap the faces and can specify ethnicity, as well as many other aspects such as facial expressions, hairstyles, facial hair, etc. It’s also possible to apply masks. This works quite well and is an extremely financially interesting alternative for the client to address this problem. The alternative would be a completely new photo shoot with ethnically adjusted models, which of course would not be cost-effective. I am neither affiliated with this company nor do I benefit from promoting it, but if you're interested, you might want to check it out.
Interesting...never tried it. Can you drop a link for us?
Love the motion reference tip for runway is great!
Put it to good use!
Midjourney seems a strange choice for consistency when there are powerful independent workflows specifically designed for the commercial world using models and powerful structuring software. I like both but certainly couldn’t use Midjourney in terms of its propensity to hallucinate and fail with key details in so much of its output. Runway is very easy to use and the output is getting much better it’s expensive like Magnific so it can be a costly learning process but very enjoyable. Krea needs to introduce privacy modes before being a consideration.
Great video. Got through 2/3 and had to hit that subscribe button so I won’t miss another one.
Not sure if you’ve covered it but the censor in MJ is an issue, so is there a tip to have a work around, such as a suggestion of what is acceptable or find out why it’s not accepted?
Dope Episode My G’s! Keep Rockin’ And I’ll Keep Watching!
Appreciate you ✌🏼thanks for hanging with us
Pure heat 🔥
🤘🏼
Guys please test the new updates on the Topaz - Its really fast and has given me great results on the Art (Pre built) model.
Noted. We’ll give it another look.
-DB
I think you have a third visitor that has something to say!
In this video you use Chatgpt to reverse-engineer an image. -Why not just use the "describe" feature in midjourney and get your prompts from there?
Mostly because it’s not nearly as effective. Until it gets an upgrade, we prefer this option.
thank you
Appreciate you ✌🏼
nice:) i like gen3 + midjourney workflow - but you need unlimited subscriptions - to achive great results you need a lot o generations. Leonardo AI has a good upscaler + Kling AI - gives me better human animation than gen3. For prompting I like claude 3.5 - instaed GPT4o.
It ain’t cheap, that’s for sure!