1. Introduction
2. Team Structure3. Process Flow
3.1. Module Learning & Experience Design
3.2. Individual Flow Design
3.3. Narrative Design & Skills Mapping
3.4. New Assets Creation
3.5. Annex: World Building - Learning & Experience Design
3.6. Annex: World Building - Story Design
3.7. Process Flow Conclusion4. Caveats
4. Caveats5. LLM Prompt Engineering Techniques
5.1. Use The Latest Model
5.2. Zero-shot Prompting
5.3. Few-shot Prompting
5.4. Chain-Of-Thought Prompting
5.5. Structuring Prompts
5.6. Describing Prompts
5.7. Editing Prompts
5.8. Extending Responses
5.9. Multiple Users Collaborating6. Text-to-Image Prompting Engineering Techniques
6.1. General Techniques
6.2. Photography
6.3. Architecture
6.4. Various Aesthetic Styles
6.5. Product & Material6.2. Photography
The following techniques are intended for Midjourney.
6.2.1. Film Types
Film Types:
- Lomography XPro 200
- Agfa Vista Plus 200
- Ilford XP2 Super 400
- Konica Infrared 750
- Kodak Vision3 500T
- Kodak Gold 200
- Fujifilm Pro 400H
- Tri-X 400
- Leica 50mm
- Fish eye camera
- Polaroid
[Shot Type] photo of [Subject], shot on [Film Type]
Refer to the following examples.
Street style photo of a woman, shot on Lomography XPro 200 --q 2 --v 4
Output:
Street style photo of a woman, shot on Kodak Gold 200 --q 2 --v 4
Output:
Street style photo of a woman, shot on Fujifilm Pro 400H --q 2 --v 4
Output:
Street style photo of a woman, shot on Tri-X 400 --q 2 --v 4
Output:
6.2.2. Lighting Styles
Lighting Styles:
- Studio lighting
- Natural lighting
- Low-key lighting
- Soft lighting
- Off-camera flash
- Backlight with hair light
- Silhouette lighting with side light
- Split lighting with rim light
[Shot Type] photo of [Subject], [Lighting Style], shot on [Film Type]
Refer to the following examples.
Street style photo of a woman, studio lighting, shot on Kodak Gold 200 --q 2 --v 4
Output:
Street style photo of a woman, natural lighting, shot on Kodak Gold 200 --q 2 --v 4
Output:
Street style photo of a woman, low-key lighting, shot on Kodak Gold 200 --q 2 --v 4
Output:
Street style photo of a woman, Soft Light, shot on Kodak Gold 200 --q 2 --v 4
Output:
6.2.3. Shot Types, Camera Position, Body Language
Shot / Closeup Types:
- Medium shot, where the subject is framed from the waist up. Used to show subject's body language.
- Closeup, where the subject fills the frame. Used to show the details and emotions of the subject.
Camera Position:
- Extreme low-angle shot / closeup or from below, taken from below the subject, making the subject appear larger and more dominant.
- Extreme high-angle shot / closeup or from above, A shot taken from above the subject, making the subject appear smaller and vulnerable.
- Wide shot, to add context for what's going on in the background.
- Center view
- Side view
- Tilt-shift
Body Language:
- Walking
- Sitting
- Standing
Emotions:
- Overjoyed
- Surprised
- Heart-broken
- Angry
Combined:
- Sitting, overjoyed, extreme low-angle, from below, center view
- Standing, angry, extreme high-angle closeup, from above, center view
[Shot Type], [Position], [Body Language & Emotions] photo of [Subject], [Lighting Style], shot on [Film Type]
Refer to the following examples.
Street style photo of a woman, medium closeup, side view, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, extreme low-angle, from below, centered view, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, extreme high-angle closeup, from above, center view, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, sitting, medium shot, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, walking, medium shot, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, angry, closeup, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, surprised, closeup, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, overjoyed, closeup, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Prompt:
Street style photo of a woman, heart-broken, closeup, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, angry, closeup, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, extreme high-angle closeup, from above, high-angle center view, natural lighting, shot on Agfa Vista 200, --v 4
Output:
Street style photo of a woman, standing, center view, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, standing, side view, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
Street style photo of a woman, walking, wide shot, new york city, natural lighting, shot on Agfa Vista 200 --v 4 --ar 16:9
Output:
6.2.4. Fashion, Color, and Textiles
Fashion, color and textiles
- Brand names: Gucci, Nike, etc
- Colours
- Material / Fabric: Linen, cotton, wool, leather, etc
[Shot Type], [Position], [Body Langauge & Emotions] photo of [Subject] wearing [Design] [Colour] [Material], [Lighting Style], shot on [Film Type]
Refer to the following examples.
Street-style photo of a young woman, yellow gucci jacket, blue gucci shirt, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9
Output:
Street-style photo of a young woman, gucci, green, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9
Output:
Street style photo of a young woman, gucci, orange, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9
Output:
Street style photo of a young woman, nike, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9
Output:
Street style photo of a young woman, gucci, white, linen, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9
Output:
street style photo of a young woman, gucci, leather, linen, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9
Output:
6.2.5. Atmosphere & Ambiance
Fashion, color and textiles
- Smokey, Misty, Steamy, Foggy
- Morning, evening
- Sunny, overcast
- Back light, side light
Including [Atmosphere] and [Ambiance]
Refer to the following examples.
Misty
Output:
Steamy
Output:
Morning fog
Output:
Evening fog
Output:
6.2.6. Create Consistent Characters
It starts with a model, and it seems to work best with a head and shoulders portrait photo like this one.
1960s street style photo of a young woman, latina, dior, silk, diamonds, dress, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9 --seed 1622
Output:
Next, copy the image URL and start a new prompt. In your prompt, include the URL, and the same prompt + seed you used to generate the image. Like this
[Insert URL] 1960s street style photo of a young woman, latina, dior, silk, diamonds, dress, wide shot, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9 --seed 1622
Output:
Now, use the same prompt format with the URL to create new environments with the same character.
Notes:
- Models that have a more unique/distinct look are more likely to result in consistent results.
- Keeping the variables similar to the prompt used to generate the original image helps
- Don't have to use the same seed, but it seems to help
- Try changing clothing, camera perspective, lighting, or location
https://s.mj.run/YuSa9350SyA 1960s street style photo of a young woman, sitting, latina, dior, silk, diamonds, natural lighting, soho, shot on Agfa Vista 200, 4k --ar 16:9 --seed 1622
Output:
https://s.mj.run/YuSa9350SyA 1960s street style photo of a young woman, sitting, park bench, latina, dior, silk, diamonds, natural lighting, central park, shot on Agfa Vista 200, 4k --ar 16:9 --seed 1622
Output:
https://s.mj.run/YuSa9350SyA 1960s street style photo of a young woman, walking, latina, dior, silk, diamonds, natural lighting, beach, shot on Agfa Vista 200, 4k --ar 16:9 --seed 1622
Output:
https://s.mj.run/YuSa9350SyA 1960s beach style photo of a young woman, sitting, latina, dior, silk, diamonds, side view, side angle shot, sunset, beach, shot on Agfa Vista 200, 4k --ar 16:9 --seed 1622
Output:
← Previous
Next →