Loading video...

Video Failed to Load

Go Home

Within two years, you can create a full game like this from scratch in less than a week. In the meantime, here's the prompt to create the images for a game like this with Midjourney 👇🏼

354,025 views • 1 year ago •via X (Twitter)

11 Comments

PJ Ace's profile picture
PJ Ace1 year ago

Isometric pixel art depiction of a traditional Japanese village during cherry blossom season, sakura petals gently falling. The player’s inventory and equipment status are displayed on the left side, with a stamina gauge and skill cooldown timers integrated along the bottom. The camera angle shows the player character practicing samurai sword techniques in the village square, with pixelated villagers observing. Soft ambient lighting complements the pastel color palette. Resolution 1920x1080, 16:9. --ar 6:5 --stylize 400 --v 7 A cozy retro Japanese town in pixel art style, viewed from an isometric angle. Cherry blossoms drift across the screen as a small train chugs along elevated tracks. The HUD displays a minimap in the top-right corner, a health bar in the top-left, and a dialogue box at the bottom. Neon signs flicker with kanji characters, casting warm glows on the cobblestone streets. --ar 6:5 --stylize 400 --v 7 Isometric pixel art screenshot of a cozy retro Japanese street at dusk, featuring narrow alleyways lined with neon-lit ramen shops and wooden houses with paper lanterns. The player character, a pixelated traveler in a kimono, stands near a small shrine emitting soft glowing light. HUD includes a health bar shaped like a koi fish, inventory slots with traditional items, and a mini-map showing nearby NPCs. Screen resolution 1280x720, with a warm orange and purple sky gradient, subtle rain effect with pixel rain drops, and UI showing quest notifications in Japanese calligraphy style. --ar 6:5 --stylize 400 --v 7 The prompts and animations were generated using Prompt Catalyst.

PJ Ace's profile picture
PJ Ace1 year ago

Full tutorial here:

ASTROMEDA - Wishlist on Steam!'s profile picture
ASTROMEDA - Wishlist on Steam!2 years ago

A small teaser of Astromeda! It's a game inspired by Pokemon, Undertale, and OneShot. Wishlist on Steam! #TrailerTuesday #indiegame #IndieGameDev #GamingNews #Steam

Jaz's profile picture
Jaz1 year ago

video chunk ≠ functional videogame

Neuravisions's profile picture
Neuravisions1 year ago

So if I start now, I might end up finishing around the same time as someone who begins two weeks before I wrap up. With tech evolving so fast, I fear it’s going to get harder for people to stay motivated for long projects.

Oboca6782 X R P's profile picture
Oboca6782 X R P1 year ago

Brilliant 🤩 and thanks for sharing.

BORED's profile picture
BORED1 year ago

Gorgeous

Toon's profile picture
Toon1 year ago

These sample clips are not a real game demo they're just generated / not playable If you want to show off new methods of game dev show real gameplay footage

alby13's profile picture
alby131 year ago

very cool!

the Rich's profile picture
the Rich1 year ago

@wwa_3

Amory Blaine's profile picture
Amory Blaine1 year ago

Stunning

Related Videos

DALL-E 3 Double Exposure Images Using ChatGPT's Custom Instructions. 🔖 Bookmark and Repost! If you find this useful, please share it with others! You can now easily create double exposure images by using the syntax Color::subject1::subject2 You can either input this directly into DALL-E 3 before generating images or incorporate it into your custom instructions. This command will automatically use the fixed prompt to generate 4 different images, each with a unique seed value. Paste this under ChatGPT's Custom Instructions or DALL-3 before starting conversation. { DE": { "Instruction": "Using will only use generic prompt and update place holder varaibles and nothing else' Genric Prompt: "Construct a [Color] double exposure image where [Subject #1] is intricately superimposed within the confines of [Subject #2], all set against a stark white background.' Create 4 images with different seeds without modifying the generic prompt." You will first create two images. Within the same request, you will generate two more without asking for any input from the user. In general, you will always create 4 images. Your response should be something like this: 'Here are the first two images along with their seed details.' You must always provide the seed number details for that image after it's rendered. Then 'I'll generate the next two images.' And finally 'Here are the remaining two images along with their seed details.' You will always use wide aspect ratio and You must always provide the seed number. When command is activated display full instruction and also confirm that you will only use genric prompt and nothing else and update only varaiable", "CommandFormat": "color::subject1::subject2", "Response": { "Initial": "Creating images based on the provided subjects...", "AfterFirstSet": "Here are the first two images along with their prompt and seed details.", "AfterSecondSet": "Here are the remaining two images along with their prompt and seed details." }, "ActivationCommand": "/activate DE" } } Example: To activate type: /activate DE Notes Start giving prompt like this blue::mountain::wolf red::city skyline::dancer green::forest::lion If you found this post helpful, don't forget to hit the like and follow buttons, and share it with others who might find it useful.

AshutoshShrivastava

34,298 views • 2 years ago