正在加载视频...

视频加载失败

返回首页

an embedding space for Midjourney srefs. search for styles using natural language scrub through aesthetic properties like warm, cool, soft, sharp, muted, vibrant, emotions. then - copy the sref and use it in a prompt.

JungleSilicon's profile picture

Silicon Jungle

9,079 subscribers

36,997 次观看 • 1 年前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

9 条评论

Silicon Jungle 的头像
Silicon Jungle1 年前

all of these images used the same prompt and seed - with a unique sref.

Silicon Jungle 的头像
Silicon Jungle1 年前

the best part? you can do embeddings math *on* midjourney styles. what’s the average of these two in the set? what do you get if you subtract heat and add cold?

Colonel Tasty🤌 的头像
Colonel Tasty🤌1 年前

You KNOW this is gonna be a banger tool when it's released. Great UX.

Silicon Jungle 的头像
Silicon Jungle1 年前

thank you!!

Dot&DM 的头像
Dot&DM1 年前

man, some people make the coolest things on the internet. it's like this mushroom hive mind!

richrd 的头像
richrd1 年前

oh yes, I neeeeed this. Thank you, pls release soon!

Silicon Jungle 的头像
Silicon Jungle1 年前

thank you!! 🙏

maxime bodereau 的头像
maxime bodereau1 年前

We have a crawling latent space on Do you want to try ? We have an api… I don’t understand how you use the Midjourney api, it doesn’t exist ?

Silicon Jungle 的头像
Silicon Jungle1 年前

i dont use the midjourney api

相关视频

THE MIDJOURNEY V6 SREF CODES COLLECTION This is the wrap-up with SREF codes. I reviewed hundreds of SREF codes and found 15 high-quality ones that work well with different subjects and look great in either photorealistic or minimalist styles. This is sufficient for my work for now. The link is in the thread. Enjoy! #midjourney
0:23

THE MIDJOURNEY V6 SREF CODES COLLECTION This is the wrap-up with SREF codes. I reviewed hundreds of SREF codes and found 15 high-quality ones that work well with different subjects and look great in either photorealistic or minimalist styles. This is sufficient for my work for now. The link is in the thread. Enjoy! #midjourney

Tatiana Tsiguleva

114,034 次观看 • 2 年前

Made a free Midjourney Style Reference Tool >15k srefs >smart AI search >view prompt + parameters >search by color, hex code, vibe, subject I also curated 5 boards to visualize the --sref's against different styles Link below. It's free and very useful
0:20

Made a free Midjourney Style Reference Tool >15k srefs >smart AI search >view prompt + parameters >search by color, hex code, vibe, subject I also curated 5 boards to visualize the --sref's against different styles Link below. It's free and very useful

Nick St. Pierre

53,687 次观看 • 1 年前

an embedding space for character archetypes in storytelling. search by character name or description. explore semantically similar archetypes by scrubbing through the map. express their vibe through color soon? merge archetypes together or deconstruct them.
0:42

an embedding space for character archetypes in storytelling. search by character name or description. explore semantically similar archetypes by scrubbing through the map. express their vibe through color soon? merge archetypes together or deconstruct them.

Silicon Jungle

150,109 次观看 • 1 年前

Used my Midjourney SREF to make a game trailer. Would you play a skating game with this aesthetic?
0:25

Used my Midjourney SREF to make a game trailer. Would you play a skating game with this aesthetic?

Morph

255,486 次观看 • 7 个月前

So you can create a multi-steps agents (unlike GPTs) in natural language using Genspark custom super agents! For example: - Analyze a codebase - Search for the latest docs - Aggregate all the informations - Produces files ready for use How to create any agent (link below)
5:18

So you can create a multi-steps agents (unlike GPTs) in natural language using Genspark custom super agents! For example: - Analyze a codebase - Search for the latest docs - Aggregate all the informations - Produces files ready for use How to create any agent (link below)

Paul Couvert

75,656 次观看 • 8 个月前

That's pretty powerful You can turn any YT video into an infographic using Nano Banana Pro in Gemini. - Copy any YT link - Paste in Gemini and ask it to analyze it (Gemini can access the video just using the URL) - Then ask for an infographic Prompt: "Generate an image of an infographic explaining the concept presented in the video."
0:37

That's pretty powerful You can turn any YT video into an infographic using Nano Banana Pro in Gemini. - Copy any YT link - Paste in Gemini and ask it to analyze it (Gemini can access the video just using the URL) - Then ask for an infographic Prompt: "Generate an image of an infographic explaining the concept presented in the video."

Paul Couvert

168,269 次观看 • 7 个月前

curl This is our Meta-Prompt. It allows LLMs to understand our Reader, Embeddings, Reranker, and Classifier APIs for improved codegen. Using the meta-prompt is straightforward. Just copy the prompt into your preferred LLM interface like ChatGPT, Claude, or whatever works for you, add your instructions, and you're set. In this example, we copied the entire prompt into Anthropic Claude and asked it to grab every sentence from Hacker News front page and visualize them using UMAP with matplotlib. This task is nontrivial as it combines multiple APIs from our Search Foundation, like Reader and Embedding where Claude may not have knowledge of. So if you asked Claude directly, it probably wouldn't give an optimal answer. But with the meta-prompt, Claude now has good knowledge about our APIs and can generate much better code! We can copy paste the code directly to Google Colab and with minimum modification, the code just works!
1:42

curl This is our Meta-Prompt. It allows LLMs to understand our Reader, Embeddings, Reranker, and Classifier APIs for improved codegen. Using the meta-prompt is straightforward. Just copy the prompt into your preferred LLM interface like ChatGPT, Claude, or whatever works for you, add your instructions, and you're set. In this example, we copied the entire prompt into Anthropic Claude and asked it to grab every sentence from Hacker News front page and visualize them using UMAP with matplotlib. This task is nontrivial as it combines multiple APIs from our Search Foundation, like Reader and Embedding where Claude may not have knowledge of. So if you asked Claude directly, it probably wouldn't give an optimal answer. But with the meta-prompt, Claude now has good knowledge about our APIs and can generate much better code! We can copy paste the code directly to Google Colab and with minimum modification, the code just works!

Jina AI

209,078 次观看 • 1 年前

What if pending delete search ranked every result by relevance? AI Search for Pending Deletes is now live. Describe what you want using natural language and get hundreds of ranked results. 🎯 Describe what you're looking for using natural language 🔍 The AI returns related names, not just exact matches 📊 Filter by TLD, length, status, watchlists, and relevance Pay once for the pull. What's your biggest domain search frustration?
0:38

What if pending delete search ranked every result by relevance? AI Search for Pending Deletes is now live. Describe what you want using natural language and get hundreds of ranked results. 🎯 Describe what you're looking for using natural language 🔍 The AI returns related names, not just exact matches 📊 Filter by TLD, length, status, watchlists, and relevance Pay once for the pull. What's your biggest domain search frustration?

Unstoppable Domains

21,403 次观看 • 1 个月前

Stop using one sref in Midjourney - use a bunch 🫣 Your signature visuals are hidden behind mixing multiple style references Steal this nostalgia look below 👇
0:36

Stop using one sref in Midjourney - use a bunch 🫣 Your signature visuals are hidden behind mixing multiple style references Steal this nostalgia look below 👇

AmirMušić

85,542 次观看 • 9 个月前

Yesterday I came across this amazing Animated Cinematic Neo-Noir style in Midjourney, and instantly saw all its potential. It was perfect for The Matrix, with a touch of John Wick 🕶️🔫 So I generated a few images, then animated them with Grok Imagine, adding some dialogue, and just like that, in a short time, I created this fun short film. This is a workflow that works really well. The key is having an eye for styles and aesthetics, being able to immediately see what they’re good for. Because styles in Midjourney can seem useless if you don’t know how to use them, and absolute magic if you do. And that’s, in my opinion, one of the most important skills an AI artist should have: a good eye, good taste, and artistic vision. 👉 If you want to know this --sref, I’ll be sharing it today with my subscribers.
0:36

Yesterday I came across this amazing Animated Cinematic Neo-Noir style in Midjourney, and instantly saw all its potential. It was perfect for The Matrix, with a touch of John Wick 🕶️🔫 So I generated a few images, then animated them with Grok Imagine, adding some dialogue, and just like that, in a short time, I created this fun short film. This is a workflow that works really well. The key is having an eye for styles and aesthetics, being able to immediately see what they’re good for. Because styles in Midjourney can seem useless if you don’t know how to use them, and absolute magic if you do. And that’s, in my opinion, one of the most important skills an AI artist should have: a good eye, good taste, and artistic vision. 👉 If you want to know this --sref, I’ll be sharing it today with my subscribers.

OscarAI

25,764 次观看 • 6 个月前

Midjourney Video + 1 hour of work = A cartoon 💎 Here's the style reference for such an aesthetics: --sref 2619557613 Prompts below 👇
0:26

Midjourney Video + 1 hour of work = A cartoon 💎 Here's the style reference for such an aesthetics: --sref 2619557613 Prompts below 👇

AmirMušić

77,337 次观看 • 1 年前

[MIDJOURNEY SREFS] AI art is evolving fast. Don’t get left behind. • Daily elite Midjourney sREFs & inspiration. • Follow now and level up.
0:27

[MIDJOURNEY SREFS] AI art is evolving fast. Don’t get left behind. • Daily elite Midjourney sREFs & inspiration. • Follow now and level up.

ibexdream

14,664 次观看 • 7 个月前

Blending sref codes in Midjourney: Step 1: Run the prompt 'test --sw 1000 --draft' multiple times. Step 2: Create pairs of sref codes (mix two codes—either similar vibe/colors or intentionally opposite). Step 3: Pick the pair you like most, but note what’s missing. Step 4: Lower --sw to 500, add your p code with --s 500, and remove --draft. Step 5: Add a third random code and iterate many times. Example: 'test --ar 3:4 --sref 3504537004 1296666443 random --profile l3h4vio --sw 500 --stylize 500 --r 10' You'll get tons of cool styles with a similar vibe, but different details.
1:02

Blending sref codes in Midjourney: Step 1: Run the prompt 'test --sw 1000 --draft' multiple times. Step 2: Create pairs of sref codes (mix two codes—either similar vibe/colors or intentionally opposite). Step 3: Pick the pair you like most, but note what’s missing. Step 4: Lower --sw to 500, add your p code with --s 500, and remove --draft. Step 5: Add a third random code and iterate many times. Example: 'test --ar 3:4 --sref 3504537004 1296666443 random --profile l3h4vio --sw 500 --stylize 500 --r 10' You'll get tons of cool styles with a similar vibe, but different details.

Tatiana Tsiguleva

13,603 次观看 • 10 个月前

Video on how to set up a pre release #Toccata $KAS node for Mac users. It is so simple to do we should have 10,000 nodes running… IzioDev -Download the software for Mac at the link in Michael’s tweet -Open the folder. Copy the file path for Kaspad -Paste it in a terminal window, press space, then type “- - utxoindex” (no space between the two dashes). -Press enter and let it run. Use a mini pc or something without a display that can run 24/7. I am using an M1 Mac Mini.
1:09

Video on how to set up a pre release #Toccata $KAS node for Mac users. It is so simple to do we should have 10,000 nodes running… IzioDev -Download the software for Mac at the link in Michael’s tweet -Open the folder. Copy the file path for Kaspad -Paste it in a terminal window, press space, then type “- - utxoindex” (no space between the two dashes). -Press enter and let it run. Use a mini pc or something without a display that can run 24/7. I am using an M1 Mac Mini.

₿RT 𐤊 🐈📈

12,166 次观看 • 1 个月前

MIDJOURNEY EDITOR TUTORIAL: IMAGE TO IMAGE Many of you have been asking for this tutorial. To be honest, it’s super simple: 1. Drag and drop a photo. 2. Write a simple prompt. 3. Add personalization, sref codes, and other parameters if needed. 4. Run the prompt multiple times with different sref codes. 5. Pick the best results. 6. Fix details in the editor or Photoshop, if needed. That’s it! Let me know, if you have questions.
1:38

MIDJOURNEY EDITOR TUTORIAL: IMAGE TO IMAGE Many of you have been asking for this tutorial. To be honest, it’s super simple: 1. Drag and drop a photo. 2. Write a simple prompt. 3. Add personalization, sref codes, and other parameters if needed. 4. Run the prompt multiple times with different sref codes. 5. Pick the best results. 6. Fix details in the editor or Photoshop, if needed. That’s it! Let me know, if you have questions.

Tatiana Tsiguleva

54,407 次观看 • 1 年前

A simple use case that highlights the interaction between Midjourney for world-building and NBP for grounding it in something tangible.
0:29

A simple use case that highlights the interaction between Midjourney for world-building and NBP for grounding it in something tangible.

Sycomore

31,995 次观看 • 6 个月前

I just built an AI-powered creative search engine with Gemini Embedding 2 + Claude Code 🤯 Drop in your UGC clips, product shots, and ad variations — then search through everything in plain English. "Show me all the unboxing clips." "Find product shots with natural lighting." "Which creator talked about sensitive skin?" All inside Claude Code. Perfect for DTC brands and agencies sitting on hundreds of creative files they can never find when they actually need them. If you're digging through a folder of random file names, scrubbing through raw footage to find that one clip, and relying on memory to track down what's already been shot... This system eliminates the entire loop: → Drop your videos, images, and docs into a project folder → One prompt to Claude Code — it builds the entire search app for you → Google's new Gemini Embedding 2 model actually watches your videos and looks at your images → It understands what's inside each file — not just the file name → Search in plain English and get back the actual assets with confidence scores No scrolling through folders. No relying on file names to find anything. No re-shooting footage you already have. What you get: → A searchable library of every creative asset your brand has ever produced → Natural language search across video, images, and documents at the same time → Results that show the actual files inline — play videos, view images, read docs → A system that gets smarter every time you add richer descriptions to your assets One free API key. No monthly subscriptions. Runs on your machine. I put together a full playbook with the exact build prompt, the setup process, and DTC/agency use cases to get this running in under 30 minutes. Want the full playbook? > Like this post > Comment "SEARCH" And I'll send it over (must be following so I can DM)
0:22

I just built an AI-powered creative search engine with Gemini Embedding 2 + Claude Code 🤯 Drop in your UGC clips, product shots, and ad variations — then search through everything in plain English. "Show me all the unboxing clips." "Find product shots with natural lighting." "Which creator talked about sensitive skin?" All inside Claude Code. Perfect for DTC brands and agencies sitting on hundreds of creative files they can never find when they actually need them. If you're digging through a folder of random file names, scrubbing through raw footage to find that one clip, and relying on memory to track down what's already been shot... This system eliminates the entire loop: → Drop your videos, images, and docs into a project folder → One prompt to Claude Code — it builds the entire search app for you → Google's new Gemini Embedding 2 model actually watches your videos and looks at your images → It understands what's inside each file — not just the file name → Search in plain English and get back the actual assets with confidence scores No scrolling through folders. No relying on file names to find anything. No re-shooting footage you already have. What you get: → A searchable library of every creative asset your brand has ever produced → Natural language search across video, images, and documents at the same time → Results that show the actual files inline — play videos, view images, read docs → A system that gets smarter every time you add richer descriptions to your assets One free API key. No monthly subscriptions. Runs on your machine. I put together a full playbook with the exact build prompt, the setup process, and DTC/agency use cases to get this running in under 30 minutes. Want the full playbook? > Like this post > Comment "SEARCH" And I'll send it over (must be following so I can DM)

Mike Futia

12,239 次观看 • 3 个月前

Lately I’ve been working on sci-fi styles with a retrofuturistic, industrial, post-human aesthetic. I develop the concept art in Midjourney and then animate it with Grok Imagine, which, with the right prompts (not easy), works really well, with that procedural and melancholic feel. Then I create music in Suno to match that atmosphere, and well, judge for yourselves, but I absolutely love this.
1:53

Lately I’ve been working on sci-fi styles with a retrofuturistic, industrial, post-human aesthetic. I develop the concept art in Midjourney and then animate it with Grok Imagine, which, with the right prompts (not easy), works really well, with that procedural and melancholic feel. Then I create music in Suno to match that atmosphere, and well, judge for yourselves, but I absolutely love this.

OscarAI

94,839 次观看 • 5 个月前