((ultra intricate details, glossy, smooth, comic style, airbrushed)),   low angle shot, Ironman in a middle-eastern battlefield, battle scared armor, scratches, scorch marks, reflections, bullet holes, burning building in the background
((ultra intricate details, glossy, smooth, comic style, airbrushed)), low angle shot, Ironman in a middle-eastern battlefield, battle scared armor, scratches, scorch marks, reflections, bullet holes, burning building in the background
((ultra intricate details, glossy, smooth, comic style, airbrushed)), (intricately detailed cyber space neon background:1.3), a young man in cyberspace, hands in his pockets, (kaleidoscopic digital geometry, virtual realities, neon abstract cubic surrealism, digital universe, binary, glowing computer code:1.4), vast digital cyberscape, (wearing normal tattered dirty cloths, hoodie:1.5)
((ultra intricate details, glossy, smooth, comic style, airbrushed)), (intricately detailed cyber space neon background:1.3), a young man in cyberspace, hands in his pockets, (kaleidoscopic digital geometry, virtual realities, neon abstract cubic surrealism, digital universe, binary, glowing computer code:1.4), vast digital cyberscape, (wearing normal tattered dirty cloths, hoodie:1.5)
((ultra intricate details, glossy, smooth, comic style, airbrushed)), a looming dark lord, 1man, (portrait:1.2), evil mage with glowing eyes, frowning detailed face, intricately embroidered robes, terrifying, dark, evil castle on a stormy night, lightening, rain, casting a spell, (glowing blood colored magic, corrupted spiraling geometry, cool vibrant crystalline fractures:1.5),
((ultra intricate details, glossy, smooth, comic style, airbrushed)), a looming dark lord, 1man, (portrait:1.2), evil mage with glowing eyes, frowning detailed face, intricately embroidered robes, terrifying, dark, evil castle on a stormy night, lightening, rain, casting a spell, (glowing blood colored magic, corrupted spiraling geometry, cool vibrant crystalline fractures:1.5),
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

UPDATED AS OF V3 READ BELOW!

(Each v3 is a stand alone model)

If you appreciate what I’m doing feel free to https://www.buymeacoffee.com/Uzia or share some of your generations! I love to see them.

(On that note though, imagery depicting sexual violence/abuse will be reported immediately.)

As of v3 Narco will become a bastion of the western comic style. There just isn't enough western styled 1.5 models out there, and Narco v3 represents the first step in making a model that retains the westerness but aims at the diversity of subject available from anime/2.5d/realism models. It ain't there yet, but I feel it's a sufficient step for a release.

Usage:

Cfg: 4 Steps: 50 Clipskip 1 and 2, both great.

Positive prompt:

((ultra detailed, glossy, smooth, comic style))...

Negative prompt:

child, childish, canvas frame, (high contrast:1.2), (over saturated:1), ((disfigured, pink eye, poorly drawn eyes)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), blurry, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy, 3d render, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame

Hi res fix (important!!!):

Quick: (less detail, flatter style): 4x-Ultrasharp - Denoise: 0.5 - Upscale by: 2 - Steps: 20

Best...mostly: (more detail, sometimes unstable, see duplicate image gallery): 4x-Ultrasharp - Denoise: 0.5 to 0.7 - Upscale by: 2 - Steps: 50

Here's a link to a tutorial that can get you started with this:

ADetailer: recommended at your discretion except for Narco Realism where I use it constantly.

Ingredients and method (bro science):

Checkpoints:

Opiate v3

Narco v2

Lysergic v2

https://civitai.com/models/86546/western-animation-diffusion

https://civitai.com/models/81270?modelVersionId=144566 (Samaritan 3d)

https://civitai.com/models/2220/babes

https://civitai.com/models/36538/noosphere

Loras:

https://civitai.com/models/8949/jim-lee-dc-comics-marvel-style-lora

https://civitai.com/models/7955?modelVersionId=9379 (Oda Non)

https://civitai.com/models/17425/3d-inspired-lora

https://civitai.com/models/82098/add-more-details-detail-enhancer-tweaker-lora

https://civitai.com/models/121745/lineart-flat-colors

Step 1: Merge a solid base model.

Step 2: then break it with Lora.

Step 3: With Supermerger merge and extract various models using the over-Loraed-model and (model name).

Step 4: Test various combinations and ratios to find preferred style.

Step 5: Rip the style out and stick it on the bones of Opiate. With Supermerger, using various block weights, produce multiple ingredients for the final product.

Step 6: Testing. Merging. Boot it out the door.

V2 and below.

Narco is one of a trinity of models that I have been working on since the start of my stable diffusion journey. It represents the middle ground between Lysergic and Opiate, excelling at the beautiful and the horrific in an illustrative style.

The preview images are cherry picked from batches of 3 and no embeddings were used.  I will say there are times when it seems to do its own damn thing, but still, I find it hits far more than it misses. Honestly, something I'm looking forward to the most by sharing it is seeing if other people can pull gold from it's murky depths or if it should be left gasping its last in a dingy alley somewhere.

On this page you will see images from both InvokeAi and A1111 but going forward I will be using only A1111 for preview images, both for my sanity and for yours. All InvokeAi images were done with either k_dpmpp_2, k_dpmpp_2_a or k_euler_a.  Some of the images I couldn’t migrate, which is a damn shame, so if any of you wonderful chaps and chapettes can recreate the goblins in A1111 I’d love to see them.

The ingredients for this mutant have been lost in the mists of my terrible memory but going forward I will be keeping a log of the changes I make.

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.