Text-to-Image
Diffusers
English
lora
stable-diffusion-xl
style
comic
comic-book
ink
halftone
illustration
cartoon
vintage
retro
primary-colors
graphic-novel
artistic
realistic
color-grading
style-lora
Instructions to use strkyyy/comic-ink-halftone with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use strkyyy/comic-ink-halftone with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("strkyyy/comic-ink-halftone") prompt = "c0m1cink, a superhero standing on a rooftop at night" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: openrail++
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: diffusers
|
| 6 |
+
pipeline_tag: text-to-image
|
| 7 |
+
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
| 8 |
+
instance_prompt: c0m1cink
|
| 9 |
+
tags:
|
| 10 |
+
- lora
|
| 11 |
+
- stable-diffusion-xl
|
| 12 |
+
- text-to-image
|
| 13 |
+
- diffusers
|
| 14 |
+
- style
|
| 15 |
+
- comic
|
| 16 |
+
- comic-book
|
| 17 |
+
- ink
|
| 18 |
+
- halftone
|
| 19 |
+
- illustration
|
| 20 |
+
- cartoon
|
| 21 |
+
- vintage
|
| 22 |
+
- retro
|
| 23 |
+
- primary-colors
|
| 24 |
+
- graphic-novel
|
| 25 |
+
- artistic
|
| 26 |
+
- realistic
|
| 27 |
+
- color-grading
|
| 28 |
+
- style-lora
|
| 29 |
+
widget:
|
| 30 |
+
- text: "c0m1cink, a superhero standing on a rooftop at night"
|
| 31 |
+
- text: "c0m1cink, a fierce dragon breathing fire"
|
| 32 |
+
- text: "c0m1cink, a detective examining a clue"
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
# SDXL LoRA: Retro Comic Book Ink & Halftone Style
|
| 36 |
+
|
| 37 |
+
## What it does
|
| 38 |
+
This LoRA injects a classic comic book style into your artwork, featuring bold black outlines, dramatic cross-hatching, and Ben-Day halftone dot shading for an authentic vintage print look with slight color misregistration.
|
| 39 |
+
## How to use
|
| 40 |
+
Trigger the effect by using 'c0m1cink' in your prompt. A suggested strength of 0.85 typically works well, but you can adjust it based on desired intensity. Use a sampler and settings that work for comic art, such as DDIM at around 30 steps.
|
| 41 |
+
## Best for
|
| 42 |
+
- Superhero scenes
|
| 43 |
+
- Fierce dragons and mythical creatures
|
| 44 |
+
- Detective stories with mystery elements
|
| 45 |
+
- Futuristic cityscapes with robots or mechs
|
| 46 |
+
- Pirate adventures on the high seas
|
| 47 |
+
## Tips
|
| 48 |
+
Use punchy primary colors to enhance the comic book feel. Experiment with different strengths of 'c0m1cink' for varying levels of comic stylization.
|
| 49 |
+
## Example Prompts
|
| 50 |
+
|
| 51 |
+
```
|
| 52 |
+
c0m1cink A dramatic portrait of a superhero in shadowy alleyway, rain-slicked cobblestones and noir lighting.
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
```
|
| 56 |
+
c0m1cink An architectural scene with towering skyscrapers in the background, a bustling cityscape at sunset, warm golden light.
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
```
|
| 60 |
+
c0m1cink Vintage comic book illustration style for an object - a sleek sports car, sharp lines and primary colors against a halftone backdrop.
|
| 61 |
+
```
|
| 62 |
+
|
| 63 |
+
```
|
| 64 |
+
c0m1cink A dynamic action scene of a hero leaping through the air, dramatic movement with bold ink outlines and vibrant color accents.
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
```
|
| 68 |
+
c0m1cink Moody comic book page depicting an eerie forest at night, moonlight filtering through branches, shadows and fog creating tension.
|
| 69 |
+
```
|
| 70 |
+
|
| 71 |
+
```
|
| 72 |
+
c0m1cink Abstract pattern inspired by Ben-Day dots and halftone shading, vivid colors swirling in a psychedelic, retro-futuristic design.
|
| 73 |
+
```
|
| 74 |
+
|
| 75 |
+
## Trigger word
|
| 76 |
+
|
| 77 |
+
Activate with `c0m1cink`. Recommended strength: **0.9**.
|
| 78 |
+
|
| 79 |
+
## Showcase
|
| 80 |
+
|
| 81 |
+

|
| 82 |
+

|
| 83 |
+

|
| 84 |
+

|
| 85 |
+

|
| 86 |
+

|
| 87 |
+

|
| 88 |
+

|
| 89 |
+
|
| 90 |
+
## Usage with `diffusers`
|
| 91 |
+
|
| 92 |
+
```python
|
| 93 |
+
from diffusers import AutoPipelineForText2Image
|
| 94 |
+
import torch
|
| 95 |
+
|
| 96 |
+
pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
|
| 97 |
+
pipe.load_lora_weights("strkyyy/comic-ink-halftone")
|
| 98 |
+
image = pipe("c0m1cink, your prompt", num_inference_steps=30).images[0]
|
| 99 |
+
```
|