Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Emm Profile picture
@emmanuel_2m
Dec 19, 2022 • 25 tweets • 11 min read • Read on X
Scrolly
This is how I generated 180 #pixelart flowers (16 types, one consistent style) in 20 min.

This 🧵is also a @Scenario_gg run-through (web app) - with the prompts I used and the step-by-step workflow.

Reach out for any questions.

#StableDiffusion #AI #AIart #Gaming #GameAssets
I started from a (royalty-free) dataset available on #Craftpix, with 10 images of pixelated flowers (such as the ones below).
Since the dimension of each image was only 32 × 32, I upscaled them 16x using @LospecOfficial, to get 512× 512 images.

Here's a before/after comparison.

Each image was sRGB / 8-bit.

I kept the grey background this time (I often remove it otherwise).
I trained a generator on @Scenario_gg (web app) with the upscaled images.

As shown in the screen recording below, launching a training takes less than 30 seconds.

I used "Art Style > Illustration" as the regularization class (more on classes later).
20 minutes later, the generator was trained and "ready for prompting" on app.scenario.gg (and also via the iOS app)

The next step is to start exploring some prompts and modifiers. It takes 30 seconds to generate a batch of 4-10 images, as shown below:
My first prompts are simple, such as "red flower, pixel art".

I also tried other modifiers, including "sRGB", "game icon", "game asset", "pixel", "8-bit", "16-bit", etc.

The goal is to gauge the quality of the generator and which modifiers should be kept going forward.
I landed on "XXX flower, pixel art, 8-bit, sRGB, icon" with "XXX" being the name or description of the flower (e.g. "white", "iris", etc).

In minutes, I could start prompting to get consistent images with the right style, and only varying "XXX“

Here's a pink rose 🌹
"Colorful Tulip, pixel art, 8-bit, sRGB, icon"
"Colorful Orchid flower, pixel art, 8-bit, sRGB, icon"
"Lily flower, pixel art, 8-bit, sRGB, icon"
"Daisy flower, pixel art, 8-bit, sRGB, icon"
"Marigold flower, pixel art, 8-bit, sRGB, icon"
"Jasmine flower, pixel art, 8-bit, sRGB, icon"
While we're here... I'm not a flower specialist. So I asked #ChatGPT to provide me with some ideas of well-known flower species.

Prompt: "list the names of 20 of the most beautiful flowers"

Done.
"Iris flower, pixel art, 8-bit, sRGB, icon"
"Peony flower, pixel art, 8-bit, sRGB, icon"
"Lavender flower, pixel art, 8-bit, sRGB, icon"

Note: it looks like the AI took "lavender" as the color of the flower, not precisely its type (genus/species).
"Hibiscus flower, pixel art, 8-bit, sRGB, icon"
"Chrysanthemum, pixel art, 8-bit, sRGB, icon"
"Clematis flower, pixel art, 8-bit, sRGB, icon
"Poppy flower, pixel art, 8-bit, sRGB, icon"
"Carnation flower, pixel art, 8-bit, sRGB, icon"
"Passion flower, pixel art, 8-bit, sRGB, icon"
I can access all my AI-generated images under the "Images" tab and also via the "Generator" icon itself.

I can easily see the prompts I used, compare batches, or download individual images (more filtering/sorting features are coming shortly).
While not all output images are perfect (some prompts could have been more precise, and some flowers could have looked better), it's still an excellent example of how to use Stable Diffusion finetunes (with @Scenario_gg) to explore a specific graphic direction, consistently.

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Emm

Emm Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @emmanuel_2m

Emm Profile picture
Jun 2
Continuing from my last threads, and sharing how to create character turnarounds with the highest consistency ✨ for:

- style ✅
- pose ✅
- character ✅

... using the #Scenario toolset to maintain all key details.

Follow the steps below 👇 - no pencil needed ✏️. Let's dive in!
⚠️ First: it's not a 'one-click-and-done' process but instead a multi-step workflow, to be tailored to your creative goals.

Second: it ensures full creative control and deliberate designs from start to finish. Randomness or chance are sidelined.

To illustrate it, I revisited 2 characters I designed five months ago: the "girl with pink hair" (), and the "sorceress with a blue hat" ()

The other 2 turnarounds ("zombie" & "ninja") had some attention yesterday with 2M+ views ()

Image
Here are the key steps to creating stunning turnaround, using #Scenario ()

1/ Train or pick a character model (A).

2/ Optionaly>, pick a style model (B). Use it to create training images for (A), or you can merge both (A + B = C) for example.

3/ Utilize the custom model (A or C) to generate consistent characters. Then select a reference image to produce initial character turnarounds in your desired poses.

4/ Refine these initial outputs using Sketching and image2image.

5/ Select the best result and refine details in the Canvas for maximum consistency.

6/ Finally, upscale your final image (up to 8K resolution.)

Here are more details 👇👇app.scenario.comImage
Read 13 tweets
Emm Profile picture
Apr 20
Designing ultra-consistent and virtually unlimited game characters in minutes with #Scenario.

Keeping it super short 😅 — because it's actually super fast🤗.
Image
Image
1/ Select your model.

You can choose from our selection of 170+ game art models on

Or, train your own to better fit your style.

I trained this model with only 12 images, originally generated using @artificialguybr's '3D Render Style' 🙏

Note: I'm intentionally training with consistent poses.

Spoiler alert 🚨: Next week, you'll be able to #upload your own models to Scenario! 🫣app.scenario.comImage
2/ Create consistent prompts.

It's best to maintain a similar structure between your prompts and captions.

I asked ChatGPT to use a format based on race, weapon, and outfit, with 50 initial prompts below👇👇.

Adjust as needed.Image
Read 10 tweets
Emm Profile picture
Mar 12
Just tested Midjourney's "Character Consistency" feature (-- cref). It's promising!

I don't think it beats a good #LoRA (yet). Especially when paired w. IP Adapter.

Below are some quick tests I ran on Scenario (high-def pics below + more updates coming👇👇)

What do you think? “A blue-skinned man with large yellow eyes, bald, wearing a BJJ gi with a black belt, raising his arm in victory on a podium, pointy ears, wrinkles, highly detailed, 35 mm, award-winning photography, bokeh, studio quality”
Left: input image
Right: MJ (--cw 0)
Image
Image
Left: input image
Right: MJ (--cw 50)
Image
Image
Read 5 tweets
Emm Profile picture
Feb 9
@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 👇👇Image
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)

Since the images were photographs, I'm creating a "mix" by adding one or two more LoRAs to the composition.

Additional LoRAs can introduce a specific style, moving away from the original photorealistic style.

You can choose platform LoRAs curated by @araminta_k and the Scenario team - See Image
Image
Read 10 tweets
Emm Profile picture
Feb 1
"3D Outfit Transformation with AI"

I trained a LoRA model on , using a 3D model of an old armor, available on Sketchfab (CC0 license).

Now, I can apply it to seamlessly "dress up“ my characters. Detailed process in the following X tweets 🧵👇 Scenario.com

Image
Image
I found this nice 3D model of an ancient medieval outfit, crafted by @Blueprint_Games and shared on @Sketchfab under the CC BY 4.0 DEED license.

You can explore it here: . sketchfab.com/3d-models/old-…
Training the model is straightforward.

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).

I selected the "Character" (= subject) preset. app.scenario.com
Image
Read 7 tweets
Emm Profile picture
Jan 18
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.Image
My prompt structure was dead simple... less than 10 words!

(type of building/scene), solid color background, highly detailed, centered. Image
Read 22 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(