Meta just launched their new AI image generator.
But how good is it?
I compared it to Midjourney, DALL-E 3 and Adobe Firefly across 10 image categories.
Here are the results:
Prompt:
A man in a coat standing in an orange sand patch, in the style of cinematic atmosphere, large-scale minimalist, hazy, movie still, red and amber, glistening, ferrania p30 --style qVdtQ60V2-8YHZ0RGqm-3UmPObQEqr-D5u2S297-4yuG4HZyCHwGsXsx-2dxwwxVFE3LC-dCqlpRRnUKWsgbGX68IwPCNVIcd-4G7sJvV0vQTb-2dQJV5KAaXqo-b7SDrORxyc24CLtaDb-qVdtQ60V2-u8riC6gsgk8-56C0nLFmcFy-qnuRTscVi-qVdtQ60V2-qVdtQ60V2-qVdtQ60V2-qVdtQ60V2-qVdtQ60V2-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-4yuG4HZyCHwGsXsx-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-qUAYQmE4i-idVqj2X05dsKPnkUmOYWMBxeLTlvnc4Vy0j2LK --ar 21:9
#midjourney
🔥 ¡¡STABLE DIFFUSION de VIDEO!! 🔥
El equipo de StabilityAI acaba de anunciar un nuevo modelo de generación de vídeo, Stable Video. El modelo se ha liberado y lo podéis descargar YA aunque su licencia no recoge uso comercial.
The upcoming GPT Store is a major opportunity, much like the early iPhone app days. People will probably turn simple ideas into millions of dollars.
I'm creating my own GPTs and have collected a few tips & tricks.
Here's what I've learned to help you get started:
Dalle3: One woman, different ages - Updated:
With the new changes to Dalle3 Seed feature, it's good to use "same seed" for ideal results.
The process is quite simple.
This is the entire chat request:
same woman, 4 different ages, 5 years, 20 years, 40 years and 60 years.
don't vary anything else just vary the age
use same seed for all images
keep the hair same, everything else same, just vary the age
If any image is not corresponding to the requested age ask Dalle to fix that image.
Yesterday, I showed you how DALL•E 3 can take your pictures to the next level.
Now, with just ONE prompt, you can create four images that range from normal to the weirdest level!
Here is the prompt:
“Another text to image model has a parameter called “weird”. The higher this parameter is, the weirder the image gets, ranging from 0 (normal) to 3000 (the weirdest).
I want you to recreate this feature. You will create four images, one at a weird level 0, one at 1000, one at 2000, and another one at 3000.
The image I want you to create is of: [desired image].”
You can also specify things you want to exclude in your prompt. For example, you can write that you don’t want your images to have a cartoonish vibe.
Below you can find more examples. I would love to see your creations too 👀
Get ready for the start of GEN:48 tomorrow morning at 9 AM EST with this new Runway Academy walking through the newly updated Text to Image model, and how to combine it with Gen-2 Image to Video for incredible results.
Most people aren't aware of DALL-E 3's full potential.
I've spent the past 3 weeks deep diving into DALL-E 3 to uncover its capabilities.
Here are my top 10 tutorials:
This might be one of the most important documentaries that anyone can watch right now given current events and escalations between Hamas, Israel, Iran, and the US.
All wars are bankers wars.
If you are still caught up in the left vs right, Israel vs Palestine, Ukraine vs Russia narratives, treating geopolitics and war as if it's a football game where you are rooting for one side to win as the real moral authority, then you need to take 45 minutes out of your day to watch this in full.
I've shared this documentary already weeks ago and a lot of people saw it and appreciated it, but I think it's now more important than ever for as many people to see it as possible and to really understand the profound and eye opening truth behind those words, and how EVERY SINGLE conflict has had powers above it funding both sides with nefarious intent behind it and a broader agenda that is not in the true interests of the people.
I don't think any of what's happening right now is organic. I don't think Hamas getting into Israel to murder and capture civilians was a mistake, nor do I think the $6bil the Biden admin unfroze for Iran in exchange for hostages before the attack was a mistake either. They're constructing narratives right in front of us and we cannot just blindly believe them on surface level evaluation, especially when these narratives are being given by the establishment and MSM.
I've said this before and I'll say it again. You need to think like they do with strategy, perception, and propagandistic motivations in mind. You need to try and understand why they are presenting whatever information to the public and for what purpose. You need to question every action, every directive, every media spin.
Why is the narrative now shifting towards Biden admin causing this attack by releasing funds to Iran? Why is Lindsey Graham pre-emptively suggesting war with Iran in conjunction with this? What if this is designed to ensure Biden attacks Iran to cover his ass in giving them $6bil back?
Also...Why was there such a huge focus of attention on anti-semitism on X in the weeks leading up to this attack? Was that organic? or was that planned in advance knowing there would be an attack on Israel and perceptions needed to be pre-emptively put in place for justifying censorship?
Question everything. Assume conspiracy.
La nueva tendencia en creación de imágenes con IA.
Puedes utilizar DALL-E 3 para crear imágenes increíbles al estilo knolling.
Es fácil y gratis, y te enseñaré cómo:
🧶HILO🧶
Yes we can create custom gift wrapping with DALLE 3 also.
"Wrapping paper design with tiling featuring a fall theme"
Such a simple prompt and excellent results.
DALL-E 3 is a great source of inspiration for product photography.
For example, you can use it to make beautiful top-down knolling style product shots.
Here's the prompt I use:
Knolling product photo of a [main object] surrounded by [secondary objects], arranged on a clean background.
You can find examples in the ALT of the pics below.
Some extra tips:
1. The main object is the item that you want to focus on.
2. The secondary objects are usually smaller, and related to the main object.
3. Use ChatGPT to give suggestions for the secondary objects.
For best results, tell GPT your main object, then ask it to:
- Select 4-5 secondary objects
- Choose visually appealing objects
- Arrange them in order of importance
That's all for now.
I hope you found this useful!
Follow me at @chaseleantj for more practical ways to use DALL-E 3.
Anyone can now use DALL-E 3 to generate stunning product photos!
Here are my top 3
Product photography compositions:
1. Front angle
2.Profile shot
3. Flat lay
Prompt formula:
(composition) (subject) (props) (background style)
For this demo, I've chosen a Halloween-themed style!
Let's fill in the blanks:
1/ front angle product shot of lipstick with pumpkin props, on a simple background
2/ profile product shot of perfume with pumpkin props, on a simple background
3/ flatlay product shot of lipstick with pumpkin props, on a simple background
I hope you found this helpful! For more practical use cases and real-life applications, follow @Salmaaboukarr for more
Next up, how to generate themed backdrops with DALL-E 3
CAMERA ANGLES IN DALL·E 3
I repeated the same experiment for DALL·E 3 that I did with Midjourney.
When I need a specific composition, I often use the following tokens:
- Macro
- Close-up
- Wide Angle
- Diagonal Angle
- Aerial
- High Angle
- Low Angle
- Oblique Angle
'High Angle' and 'Low Angle' work well in DALL·E 3. The other tokens are less effective, but from time to time, they work 😀