Daniel and I worked on a specific dataset of stylized characters (a style exploration, made a few years ago).
I focused on the characters below (removed the weapons, beast, and badges) and trained a finetune using @Scenario_gg on 7 images.
It started really simple, and I kept a basic prompt for most of the exploration.
"A character". Just this. And I ran a dozen batches.
Most of the output were OK (80%-ish) but then I removed the weird ones.
And here you go. 81 characters, AI-generated from @DanielPlaychain's art.
Quick comparison of the closest original asset, and a randomly AI-generated asset:
Some other close-up views (AI-generated too)
Then I tried making other variation by "forcing" the AI to draw a female character (elf-like)
"Character, elf, female"
Or an orc ("Character, orc")
Or a wizard 🧙
I generated variations around the "gremlin/little creature" using img2img
Made more orc-like creatures, also with img2img.
And even tried getting other shapes/silhouettes, still using img2img.
This was a very quick - and yet quite exciting experiment.
In that particular case, the output might not be final art (i.e. production-ready). Yet, it's a simple demonstration of how artists can use their own work to explore more creative options for their customers.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
@ClaireSilver12 - (I hope you don't mind me RT this for a broader reach and to share it with more users.)
Here's an advanced use case for the IP Adapter. You can adjust or remove the steps depending on the desired output/goal. Bear with me; it's actually quite straightforward.
1 - Train a LoRA on a specific subject (e.g., character).
2 - Blend the LoRA to perfectly capture the style (e.g., comic, cartoon, oil painting, 3D...).
3 - Run inference on that "blended" model.
4 - Select an image that stands out and use it as a reference with the IP Adapter.
5 - Modify the prompt to create variations of the subject.
Let's get started 👇👇
1/ The first step is to train one (or more LoRA) models on a specific subject (e.g. character or object), or also a style.
The process is straightforward. I'll use the example of the "girl with pink hair" (😊🫠) that I shared before (12 training images)
Simply select "New Model - Train" on . I use 9 images of the model, showcasing various angles and zoom levels, accompanied by concise captions (details below).
This could be the best model I've ever created for generating isometric buildings, on Scenario.
Output consistently match the style I wanted, and the model responds perfectly to (short) prompts, without any reference images needed.
It's a LoRA composition. More below.
Process: it's pretty simple.
I created a LoRA composition from 4⃣ distinct LoRA.
(i) - My own "Fantasy Buildings" LoRA
(ii) - Three LoRAs available on #Scenario: "Isometric Storybook", "Stylized Fantasy Iconic Imagery" and "Belgian School Comics".
The influence of each LoRA is below.
My prompt structure was dead simple... less than 10 words!
(type of building/scene), solid color background, highly detailed, centered.
2024 will be the year of AI #influencers... Fully generated characters that can engage, entertain, and earn!
They're not just a concept anymore; some are already seeing significant revenue.
You can create one today. Learn how to build it from A to Z, including all aspects of visual storytelling, in just 30 minutes on #Scenario. 🌟👇
Just follow the steps below (or bookmark for later) 🧵
#GenAI will drive the emergence of virtual influencers
Take Lil Miquela, a computer-generated character with 2.6M followers, working with Burberry, Prada, or Givenchy, securing deals worth hundreds of thousands of dollars.
Or Kyra, India's pioneering virtual influencer, boasting over 200k followers and numerous brand endorsements.
More recently, Aitana López, a Spanish GenAI model created by The Clueless agency, gathered 253K followers, reportedly earning up to $11k monthly.
Other virtual stars include Lu do Magalu, Imma, Shudu Gram and this is just the beginning, here's why ⏬
Crafting an AI influencer means meticulous control for both the character details and the visual storytelling.
Maintaining the control & consistency can be daunting, and simply relying on prompts can prove to be quite challenging.
Enter : Unlock unparalleled consistency by training custom AI models, directly from your web browser, all without requiring dedicated hardware or complex local setup.Scenario.com