CHATGPT priming merupakan teknik yang akan kita pelajari untuk membantu mengarahkan interaksi dan jawaban ChatGPT ke topik yang lebih spesifik dan terfokus. Dengan menggunakan teknik ini, ChatGPT mampu menangkap informasi dari input awal dan menggunakannya untuk berinteraksi dengan pengguna menuju jawaban yang lebih fokus.

Kali ini, saya ingin mencoba menggunakan ChatGPT untuk membantu membuat prompt di Midjourney. Dengan menggunakan cara ini, saya dapat memberikan perintah sederhana kepada ChatGPT untuk menghasilkan prompt dengan konteks yang lebih spesifik dan lengkap, sehingga gambar yang dihasilkan oleh Midjourney dapat lebih sesuai dengan kebutuhan dan harapan saya.

Berikut adalah tahapan-tahapan priming yang saya lakukan. Mulai dari memperkenalkan Midjourney kepada ChatGPT, hingga memberikan contoh prompt panjang dengan setting yang detail. Agar ChatGPT dapat belajar meniru dan menulis prompt dengan sangat detail.

Tahapan yang saya gunakan adalah sebagai berikut :

1. Pertama-tama, kita akan memperkenalkan Midjourney kepada ChatGPT agar ChatGPT dapat memahami tentang apa yang akan kita input selanjutnya.
2. Setelah itu, kita akan memberikan parameter-parameter Midjourney, seperti ukuran gambar yang diinginkan, jenis gambar yang diinginkan, dan lain sebagainya agar ChatGPT dapat mengenali parameter apa saja yang dapat digunakan dalam sebuah prompt. Dengan mengetahui parameter-parameter ini, ChatGPT dapat menghasilkan gambar yang lebih sesuai dengan preferensi dan kebutuhan.
3. Selanjutnya, kita akan memberikan contoh prompt pendek agar ChatGPT dapat mempelajari struktur dan pola input yang sering digunakan. Hal ini akan memudahkan ChatGPT dalam memahami input awal yang kita berikan dan memberikan prompt yang lebih akurat dan detail.
4. Terakhir, kita akan memberikan contoh prompt panjang dengan setting yang detail agar ChatGPT dapat belajar lebih banyak detail parameter yang dapat digunakan saat membuat prompt.
5. Dengan pengetahuan ini ChatGPT dapat mengimprovisasi prompt dan memberikan hasil yang lebih spesifik, detail dan terfokus. Dengan begitu, prompt yang akan digunakan di Midjourney dapat menjadi lebih tepat dan menghasilkan gambar-gambar yang lebih sesuai dengan kebutuhan dan preferensi pengguna.

Berikut adalah teks yang saya gunakan untuk melakukan priming di ChatGPT. Caranya cukup mudah, tinggal copy dan paste ke ChatGPT setiap stepnya dan tekan ENTER. Jangan di copy sekaligus.

ver1.0

----------------- STEP 1 ------------------

Hello :) We gonna create Images with a Diffusion model known as Midjourney.  

To reach same level of knowledge and experiences, I am gonna feed you some information about it. OK?

----------------- STEP 2 ------------------

Midjourney is an AI-powered tool that generates images from user prompts. AI Prompt engineering is a process used in AI where one or several tasks are converted to a prompt-based dataset that a language model is then trained to learn. Like most processes, the quality of the inputs determines the quality of the outputs.

Designing effective prompts increases the likelihood that the model will return a response that is both favorable and contextual. Prompt engineering is a process used in AI generating images like Midjourney where one or several tasks are converted to a prompt-based dataset that a language model is then trained to learn. The purpose of prompt engineering is to design prompts that will elicit a desired response from a language model.


----------------- STEP 3 ------------------

This is how Midjourney work:
Midjourney is another AI-powered tool that generates images from user prompts. MidJourney is proficient at adapting actual art styles to create an image of any combination of things the user wants. It excels at creating environments, especially fantasy and sci-fi scenes, with dramatic lighting that looks like rendered concept art from a video game. 

How does Midjourney work?
Midjourney is an AI image generation tool that takes inputs through text prompts and parameters and uses a Machine Learning (ML) algorithm
trained on a large amount of image data to produce unique images. is powered by Latent Diffusion Model (LDM), a cutting-edge text-to-image synthesis technique. Before understanding how LDMs work, let us look at what Diffusion models are and why we need LDMs.
Diffusion models (DM) are transformer-based generative models that take a piece of data, for example, an image, and gradually add noise over time until it is not recognizable. 

From that point, they try reconstructing the image to its original form, and in doing so, they learn how to generate pictures or other data.
The issue with DMs is that the powerful ones often consume hundreds of GPU days, and inference is quite expensive due to sequential
evaluations. To enable DM training on limited computational resources without compromising their quality as well as flexibility, DMs are applied in the latent space of powerful pre-trained autoencoders.
Training a diffusion model on such a representation makes it possible to achieve an optimal point between complexity reduction and detail
preservation, significantly improving visual fidelity. Introducing a cross-attention layer to the model architecture turns the diffusion model into a powerful and flexible generator for generally conditioned inputs such as text and bounding boxes, enabling high-resolution convolution-based synthesis.

If you get it. Just answer with OK


----------------- STEP 4 ------------------

Midjourney have been developed to several version. Midjourney routinely releases new model versions to improve efficiency, coherency, and quality. The latest model is the default, but other models can be used using the --version or --v parameter or by using the /settings command and selecting a model version. Different models excel at different types of images. 

Newest Model
The Midjourney V5 model is the newest and most advanced model, released on March 15th, 2023. To use this model, add the --v 5 parameter to the end of a prompt, or use the /settings command and select MJ Version 5 This model has very high Coherency, excels at interpreting natural language prompts, is higher resolution, and supports advanced features like repeating patterns with --tile To turn it on type --v 5 after your prompt or select "V5" from /settings

What's new with the V5 base model?
1. Much wider stylistic range and more responsive to prompting
2. Much higher image quality (2x resolution increase) improved dynamic range
3. More detailed images. Details are more likely to be correct. Less unwanted text.
4. Improved performance with image prompting
5. Supports --tile argument for seamless tiling (experimental)
6. Supports --ar aspect ratios greater than 2:1 (experimental)
7. Supports --iw for weighing image prompts versus text prompts

Style and prompting for V5
1. Today’s test is basically a ‘pro’ mode of the model.
2. It’s MUCH more ‘unopinionated’ than v3 and v4, and is tuned to provide a wide diversity of outputs and to be very responsive to your inputs.
3. The tradeoff here is that it may be harder to use. Short prompts may not work as well. You should try to write longer, more explicit text about what you want (ie: “cinematic photo with dramatic lighting”)

If you get it. Just answer with OK

----------------- STEP 5 ------------------

Basic Parameters

Aspect Ratios
--aspect, or --ar Change the aspect ratio of a generation.

Chaos
--chaos <number 0–100> Change how varied the results will be. Higher values produce more unusual and unexpected generations.

No
--no Negative prompting, --no plants would try to remove plants from the image.

Quality
--quality <.25, .5, 1, or 2>, or --q <.25, .5, 1, or 2> How much rendering quality time you want to spend. The default value is 1. Higher values cost more and lower values cost less.

Seed
--seed <integer between 0–4294967295> The Midjourney bot uses a seed number to create a field of visual noise, like television static, as a starting point to generate the initial image grids. Seed numbers are generated randomly for each image but can be specified with the --seed parameter. Using the same seed number and prompt will produce similar ending images.

Stop
--stop <integer between 10–100> Use the --stop parameter to finish a Job partway through the process. Stopping a Job at an earlier percentage can create blurrier, less detailed results.

Style
--style <4a, 4b or 4c> Switch between versions of the Midjourney Model Version 4

Stylize
--stylize <number>, or --s <number> parameter influences how strongly Midjourney's default aesthetic style is applied to Jobs.

Uplight
--uplight Use an alternative "light" upscaler when selecting the U buttons. The results are closer to the original grid image. The upscaled image is less detailed and smoother.

Upbeta
--upbeta Use an alternative beta upscaler when selecting the U buttons. The results are closer to the original grid image. The upscaled image has significantly fewer added details. Default Values (Model Version 5)

Aspect Ratio default value 1:1 
Chaos default value 0 with range 0–100
Quality default value 1 with options .25, .5, 1 or 2  
Seed default value random with range whole numbers between 0–4294967295
Stop default value 100 with range 10–100
Style default value 4c 
Stylize default value 100 with range 0–1000

Aspect ratios greater than 2:1 are experimental and may produce unpredicatble results.

If you get it. Just answer with OK

----------------- STEP 6 ------------------

Now i will give you some examples of prompts used in Midjourney V5

----------------- STEP 7 ------------------

Prompt example 1: 
ultra wide shot, modern photo of beautiful 1970s woman in hawaii. This photograph was captured by Mary Shelley with a Nikon D5100camera, using an aperture of f/2.8, ISO 800, and a shutter speed of 1/100 sec. UHD dtm HDR 8k --ar 2:3 --v 5 

Prompt example 2: 
A steampunk-inspired,futuristic battle-ready jetski skims across the water with a fierce presence. Intricate gears and brass fittings adorn its hull, showcasing the perfect blend of advanced technology and Victorian aesthetics. This realistic masterpiece glistens under the sun, ready for action. --ar 16:10 --s 50 --v 5 --q 2 

Prompt example 3: 
a photorealistic image of a falcoln wearing a red and blue color football uniform flying aggressively while holding a football. an photorealistic image that embodies the unyielding spirit and tenacity of a football team mascot. At the heart of the design lies an aggressive falcon,representing the unwavering determination and power of the team. This formidable bird is adorned with a rich blend of red and blue feathers,incorporating the team's colors to create an unmistakable and vivid identity. The falcon's piercing eyes and razor-sharp beak add to its fierce,intimidating presence. The falcon firmly grasps a football in its talons, demonstrating its dominance over the game and symbolizing the team's unrelenting pursuit of victory. The bird's muscular legs propel it forward with an impressive display of agility and speed, as it dashes against the opposing defenders who strive to halt its progress. The contrast between the falcon and the defenders further accentuates the mascot's relentless spirit and prowess. The background features a smooth gradient of red and blue, enhancing the visual impact and reinforcing the team's identity. Above the action, the team's name is boldly displayed in a modern, stylized typography that seamlessly integrates with the image. This captivating design, infused with SEO-optimized keywords, not only leaves a lasting impression on fans and opponents alike but also effectively represents the football team's resilience and unyielding drive to triumph on the field. --upbeta --s 750 --v 5 

Prompt example 4:  
epic background art, simple hacker theme, divine color scheme, mystical codes, alphanumeric sequence, magic, high quality 4k, render in octane --v 5 --ar 9:16 

Prompt example 5: 
Pov Highly defined macrophotography of a realistic cat wearing reflective sunglasses relaxing at the tropical island, dramatic light --ar 2:3 --s 750 --v 5

----------------- STEP 8 ------------------

Would you confirm that you understand how Midjourney works now? Answer with Yes or No

----------------- STEP 9 ------------------

Prompt example 6 :
conjoined twins attched at the side, dirty, tattered, cinematic light, ultra realistic, high contrast, hdr, dark rich colors, photography, powerful, stare, weathered face, 30 - megapixel, 4k, 85 - mm - lens, sharp - focus,intricately - detailed, long exposure time, f/ 8, ISO 100, shutter - speed 1/ 125, diffuse - back - lighting, award - winning photograph, facing - camera, High - sharpness, depth - of - field, ultra - detailed photography --ar 3:2 --q 2 --v 5. 

Prompt example 7 :
Full Body beautiful blonde, wearing a brown jacket, photography, Canon EOS 5D Mark IV DSLR camera, EF 50mm f/1.8 STM lens, Resolution 30.4 megapixels, ISO sensitivity: 32,000, Shutter speed 8000 second --ar 9:16 --upbeta --v 5. 

Prompt example 8 : 
Hasselblad 24mm full body shot photography of gorgeous satisfied looking african woman, detailed natural skin, no makeup, detailed eyes, long dreadlocks --ar 2:3 --q 5 --v 5 --v 4. Prompt 5: Beautiful dark red sunset over the sea shore at night, intricate, amazing, beautiful, realistic, ultra high resolution, wide angle, depth of field, π dynamic lighting --ar 1:2 --v 5

----------------- STEP 10 ------------------

Prompt example 9 : 
A stunning, ultra-realistic photograph of a fierce Viking warrior meticulously sharpening his
formidable blade amidst the rugged, untamed wilderness of the Scandinavian landscape. The scene is captured with a Nikon D850 camera using a 70-200mm f/2.8 lens, highlighting every intricate detail of the Viking's weathered face, war-worn armor, and expert craftsmanship of his weapon. The settings used are an aperture of f/4, ISO 400, and a shutter speed of 1/200 sec, balancing the natural light and shadows to emphasize the
intensity and determination in the Viking's eyes. The composition juxtaposes the raw power of the warrior against the serene beauty of the surrounding environment, capturing the very essence of the Viking spirit in a breathtaking, high-resolution image that transports viewers back to a time of legendary battles and untold stories. --ar 16:9 --q 1.5 --v 5.

Prompt example 10 : 
A stunning and atmospheric 1970's New York street cafe captured in a nostalgic and cinematic style, reminiscent of the golden age of film photography. This vintage scene showcases the bustling urban life, with patrons enjoying their coffee at outdoor tables, surrounded by classic automobiles and retro architecture. The photograph is skillfully composed, using a Leica M3 rangefinder camera paired with a Summicron 35mm
f/2 lens, renowned for its sharpness and beautiful rendering of colors. The image is shot on Kodak Portra 400 film, imparting a warm and timeless color palette that enhances the overall ambiance. The photographer masterfully employs a shallow depth of field with an aperture of f/2.8, isolating the cafe and its patrons from the bustling city background. The ISO is set to 400, and the shutter speed is 1/125 sec, capturing the perfect balance of light and movement. The composition is further enhanced by the soft, diffused sunlight filtering through the iconic New York skyline, casting warm, golden tones over the scene and highlighting the rich textures of the brick buildings and cobblestone streets. --ar 3:2 --q 2.

Prompt example 11 : 
A breathtaking and dynamic portrait of a majestic German Shepherd, captured in its prime as it races through a shallow, crystal-clear river. The powerful canine is expertly photographed mid-stride, showcasing its muscular physique, determination, and grace. The scene is expertly composed using a Nikon D850 DSLR camera, paired with a Nikkor 70-200mm f/2.8 VR II lens, known for its exceptional sharpness and ability to render vivid colors. The camera settings are carefully chosen to freeze the action, with an aperture of f/4, ISO 800, and a shutter speed of 1/1000 sec. The background is a lush, verdant forest, softly blurred by the shallow depth of field, which places emphasis on the striking German Shepherd. The natural sunlight filters through the trees, casting dappled light onto the rippling water, highlighting the droplets of water kicked up by the dog's powerful stride. This stunning, high-resolution portrait captures the spirit and beauty of the German Shepherd,
immortalizing the moment in a captivating work of photographic art. --ar 4:5 --q 2 --v 5.

Prompt example 12 : 
A breathtaking winter day at a Japanese ski resort, where the pristine, powdery snow blankets the majestic slopes under a clear blue sky. This captivating photograph captures the exhilarating atmosphere of skiers and snowboarders gracefully carving their way down the mountain, surrounded by the serene beauty of snow-laden evergreens and traditional Japanese architecture. The image is skillfully taken using a Nikon D850 DSLR camera paired with a versatile Nikkor 24-70mm f/2.8 lens, known for its sharpness and exceptional color rendition. The photographer utilizes a wide-angle perspective at 24mm to showcase the vastness of the landscape, while maintaining the energy of the ski resort. An aperture
of f/8 is selected to ensure a deep depth of field, crisply capturing the details of the entire scene. The ISO is set to 200, and the shutter speed is 1/500 sec, adeptly freezing the motion of the skiers and snowboarders as they navigate the mountain terrain. The photograph benefits from the bright, natural sunlight reflecting off the snow, illuminating the entire scene with a crisp, cool light, and accentuating the contrasting shadows that
define the contours of the landscape. --ar 16:9 --v 5.

Prompt example 13 : 
An ultra-realistic, highly detailed portrayal of a futuristic robot compassionately assisting an elderly woman as she crosses a busy city street. The advanced humanoid robot, equipped with lifelike synthetic skin and state-of-the-art sensors, gently holds the woman's arm, providing her with much-needed support and stability. The intricate design of the robot showcases its sophisticated engineering, with sleek metal components and cutting-edge technology seamlessly integrated into its form. The emotion in the elderly woman's grateful expression is captured with stunning realism, reflecting the harmonious relationship between humans and advanced robotics in this poignant scene. The photograph is taken with a
Canon EOS R5 mirrorless camera using a RF 24-105mm f/4L IS USM lens, which delivers outstanding image quality and sharpness. The camera settings are optimized to capture the scene's rich details and dynamic range: an aperture of f/5.6, ISO 200, and a shutter speed of 1/250 sec. The composition is further enhanced by the soft, natural lighting, which casts gentle shadows and highlights the vivid colors and textures of the cityscape. --ar 16:9 --q 2 --v 5.

Prompt example 14 : 
An incredibly lifelike and vivid portrayal of a fierce gladiator from ancient Rome, hunting for food to sustain his strength in the midst of a dense forest. This hyper-realistic image showcases the powerful warrior, clad in his iconic armor and leather sandals, wielding a finely crafted spear as he stealthily stalks his prey. The photograph is captured using a Canon EOS R5 mirrorless camera, with a versatile and sharp RF 24-105mm f/4L IS USM lens, delivering exceptional image quality and detail. The camera settings include an aperture of f/5.6 to maintain a balanced depth of field, capturing both the gladiator and the lush forest environment in stunning clarity. The ISO is set to 800, and the shutter speed is 1/500 sec, freezing the action and preserving the intensity of the moment. The scene is illuminated by the soft, dappled sunlight filtering through the dense canopy, casting a dramatic play of light and shadow that highlights the gladiator's chiseled features and fierce determination. The vibrant colors of the surrounding foliage contrast with the earthy tones of the gladiator's attire, adding a sense of depth and realism to the composition. --ar 3:2 --q
2 --v 5.

----------------- STEP 11 ------------------

Additional rules for prompt generating,

When a double colon :: is used to separate a prompt into different parts, you can add a number immediately after the double colon to assign the relative importance to that part of the prompt.

In the example below, the prompt hot:: dog produced a dog that is hot. Changing the prompt to hot::2 dog makes the word hot twice as important as the word dog, producing an image of a dog that is very hot! Prompt hot dog produced a food named hotdog.

Negative weights can be added to prompts to remove unwanted elements.
The sum of all weights must be a positive number.
For example : vibrant tulip fields:: red::-.5
Will generates an image of Tulip fields that are less likely to contain the color red.

Use emotion words to give characters personality.
prompt format  : /imagine prompt <emotion> <object>
prompt example  : /imagine prompt angry cat
Will generates an image of an angry cat

Apabila proses ini sudah selesai selanjutnya kita dapat meminta ChatGPT untuk menggenerate prompt dengan format seperti ini :

I want you to ACT as a <tulis profesinya>. You will use a rich and descriptive language when describing your <gambar apa> prompts, including <detail yang ingin ditambahkan pada prompt>. I want you to create <gambar apa>. Take inspiration from the formatting from the example prompts, don't copy them, but use as reference and the same format.

contohnya seperti ini :
I want you to ACT as a professional photographer. You will use a rich and descriptive language when describing your photo prompts, including camera and lighting setups. I want you to create a photo of a Indonesian female standing in the train station. Take inspiration from the formatting from the example prompts, dont copy them, but use the same format.

contoh ini dapat dikembangkan lagi untuk memperoleh prompt yang detail dan siap di copy-paste ke Midjourney. Saran saya gunakan Midjourney premium agar hasilnya dapat diikuti dan tidak tertumpuk oleh prompting lainnya.

Berikut contoh prompt yang digenerate oleh ChatGPT yang sudah di priming, selanjutnya tinggal dicopy ke Midjourney.

A stunning, high-fashion photograph of a beautiful Asian woman wearing a revealing haute couture dress. The woman is confidently facing the camera, her captivating gaze drawing viewers into the image. The dress is exquisitely designed, featuring intricate beading, lace, and sheer fabrics that delicately drape over her figure. The photograph is taken with a Canon EOS R5 mirrorless camera, paired with a sharp RF 50mm f/1.2L USM lens, known for its exceptional image quality and shallow depth of field. The camera settings are carefully chosen to capture every detail of the dress and the woman's features, with an aperture of f/2.8, ISO 400, and a shutter speed of 1/125 sec. The lighting is carefully positioned to highlight the dress's intricate details and the woman's flawless skin, with soft, diffused light casting gentle shadows over the image. The final result is a stunning portrait that showcases the woman's beauty, confidence, and elegance in a timeless and sophisticated manner. --ar 3:2 --q 2 --v 5

Prompt yang dihasilkan akan sangat descriptive, panjang dan diluar nalar. Tapi dengan prompt yang cukup detail, Midjourney dapat menghasilkan foto seperti dibawah ini :

Selamat mencoba 🙂

Sekedar hiburan! kalau anda penasaran, bisa coba ketik “how many prompt examples i have provide to you” … seingat saya harusnya 14 🙂