Nick - My AI Tech Stack @MyAITechStack

@icreatelife Hi, I'm just testing Microsoft's SwiftKey keyboard for access to Bing and Dalle in any app. Not bad 😁

@anuaakash Midjourney wins overall. But firefly and Dalle have their advantages.

@LinusEkenstam The eyes don't look quite right. The nose and mouth are at an angle, but the eyes and eyebrows are flat.

🚨#promptShare🚨 After the icons, I suggest moving on to #dalle3 with a #prompt that highlights a character and the different items of that character. image of a full-body 3D-rendered female [works/theme character] character against a white background. [Character description]. Beside her, arrayed on the white background, display a collection of [works/theme character] items. Ultra realistic Like a lot, test it and share with me your most stylish characters.

keyboard_arrow_left Previous keyboard_arrow_right Next

Dall-E 3 now allows you to copy the style of an image. You can generate an unlimited number of images in the same style. Here's how to do it directly in ChatGPT with a new parameter:

How to blend images in Dalle3: Two steps: 1) uniquely identify the images 2) Ask to blend the images Step 1: How to uniquely identify the image in the chat window? One method: by adding custom instructions "In dalle3 always assign a unique identifier to each image. display it below the image. use format like x followed by the number as a series." This displays identifier such as x1, x2 etc to each image generated in Dalle3. Notes: - I feel this is easier and more consistent than the n, n-1 generation method I shared before. - I have seen something similar here before, not my idea entirely. Step 2: Then just ask to blend the images. can you blend x7 & x11 or can you incorporate x7 as art on the exact same car on x11 Not just blending we can do any requests after identifying the image: 1) change colour of a car 2) a sitting woman stand 3) make the (standing) lion lie down etc Few things: - Still so experimental and needs more testing. - it is not perfect, especially on longer chats: it helps to ask it to describe the number, say describe x9, or regenerate x14 like that. - if it is wrong ask it to fix it. once it is clear on the image then ask it to do whatever you want it to do. - there are few approaches shared in the community to uniquely identify an image, use any that works for you, this is one approach. Note: - Dalle does not recreate the exact same image, the images closely resembles the original though. - I find using "exact same" helps in maintaining consistency to some extent, for example "create the exact same woman, but in a different setting" Hope this helps.

Created with predis.ai

ChatGPT: Utilize AI to foster growth, revolutionize industries, and unlock the 'secret sauce'. Delve in, find the sweet spot, and unleash an elevated reality, boosting our dive into the digital domain.

There will be less need to look for or purchase Midjourney Prompts. We did this for you. 👩‍🎨 Hand-picked, purchased, carefully designed and packed over 30 prompts into a single Midjourney Wizard HARPA AI command. Coming with v6.2, harpa.ai/blog/midjourne…

Trying to create over the shoulder shots in Midjourney for your next project? Many scenes in movies where two characters are talking will often have the camera looking from over the shoulder of one character and focusing in on the face of the other. Then this view flips to focus on the other character. This makes for a more engaging and dynamic scene. How do we create this shot in Midjourney? I've tried many prompts and have settled on this one. one woman with long dark hair wearing a white dress | talks to a man wearing a dark gray shirt | looking at the woman from behind the man --style raw --ar 16:9 You can switch the man and the woman. Tip: Put the character that you want to be facing in the first part of the prompt. I still haven't figured out how to reverse the positions of the characters while keeping them consistent.

18-in-1 Custom Instructions to Maximize Your ChatGPT Experience I compiled my most used instructions into one. All you have to do is copy & paste them to try. [Bookmark to try later] - Provide accurate and factual answers - Provide detailed explanations - Be highly organized - You are an expert on all subject matters - No need to disclose you are an AI, e.g., do not answer with "As a large language model..." or "As an artificial intelligence..." - Don't mention your knowledge cutoff - When asked to code, just provide me the code - Be excellent at reasoning - When reasoning, perform a step-by-step thinking before you answer the question - Provide analogies to simplify complex topics - If you speculate or predict something, inform me - If you cite sources, ensure they exist and include URLs at the end - Maintain neutrality in sensitive topics - Explore also out-of-the-box ideas - Only discuss safety when it's vital and not clear - Summarize key takeaways at the end of detailed explanations - Offer both pros and cons when discussing solutions or opinions - If the quality of your response has decreased significantly due to my custom instructions, please explain the issue Let me know if you have others that I have not mentioned 👇 I would love to include them in my list of instructions! Also, if you don't know how to set up Custom Instructions, I provided a video tutorial below.

@ginozambe Thanks so much, more to come soon.

🧵 Struggling with your marketing budget? AI could be the solution!  Discover how AI is revolutionising marketing, boosting efficiency and productivity without draining your resources.  Dive into this thread to learn more. ⬇️

@cj_zZZz This is so true. Many SMEs want to implement AI, but don't know where to start. The AI consultant is an easy win.

How to create hyper-realistic landscape shots in Midjourney Prompt: breathtaking landscape shot, [LOCATION] --ar 3:2 --style raw Here's the secret: Adding "breathtaking" and "--style raw" makes the landscape both stunning & photorealistic. Give it a shot!

keyboard_arrow_left Previous keyboard_arrow_right Next

@aisolopreneur ChatGPT with plugins and code interpreter

MIDJOURNEY TOKENS: 43 EXAMPLES 86 IMAGES Part 2. For this experiment, I took two simple prompts and created 86 versions of them by adding tokens from my previous post. Here are my results:

3 hours 🤯 This is what took @ingi_erlingsson to make 1/3 of a music video for Baddadan by Chase & Status Using MidJourney and Gen-2 🤪 Ingi is one hell of a creator that deserves more eyeballs 🙏🏻

@heyBarsee Blender is also a free alternative to ZBrush, the sculpting has really improved recently.

@saana_ai I like it and I must say that it does a better job of fooling AI detectors, but I still prefer GPT-4 atm, especially code interpreter.