Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
contact.safetensors
9 MB · SafeTensor · fp16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<comics-contact>
About This Model
STABLE DIFFUSION 1.5 · LoRAs
Created by
Inzaniak
on Civitai
General LoRa guide: # Poor quality or broken renders → Lower LoRa weight, try those: ← Some only work with a weight this low # Mangled limbs, general chaos → Some LoRas can’t handle rendering with resolutions bigger than 512x512 // Also make sure your prompt isn’t too complicated for this LoRa # No visible effect → Check if the LoRa has any triggers that need to be added in order to activate it # Good full models to try out LoRas with: anime → comics → semi-real → realistic →
Creator notes
What's this LoRA This is a LoRA trained on a particular style. It is an illustration style more oriented to western cartoons. The images in the examples are created using only this LoRA and different models (mainly my customs: and ) You don't need to specify a word to trigger this LoRA. The LoRA works well on NSFW (check last examples). The images are created using different weights (you can check on the image generation panel) Different Flavors My LoRAs are usually trained on AI generated images in two different steps. The first training uses images generated using a model (I choose it based on what I'm going to build) with a size of 512x768, and this is usually 10 images with different content but a similar style. The second training is based on pictures generated using the LoRA from the first step. This is done at a higher resolution (768x1152) and the output is usually upscaled using img2img. The LoRA is available in two different flavors: - RAW: This is based on the first batch of images, it has usually a more creative output, but usually needs hiresfix or img2img to really shine - Standard: This is based on the second batch of images, it has usually a less creative output, but way more stable. Here's a quick comparison (not cherry-picked): RAW: Standard: Guides Learn how to create pictures like mine with my step-by-step tutorials: - - - - If you want to create images with a high LoRA weight, I highly suggest you to check the tutorial. Support If you want to support my work, you can check out my music here: You can also check my AI Art accounts, where you'll find daily pictures made with my models (and previews of new ones coming): - -
1,672 downloads · 156 likes on Civitai
SHA256
D14F7146222DC0CB1E74D1A092A6479B5C440EF7414CF90ED4863B056999DAE5
ModelTrends.ai Model ID
#549
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DDIM
Steps
30
Guidance
8
Seed
3827093206
Size
768x1152
Clip skip
2
Prompt
girl, (skimpy:1.2), (Neon,Plain Background:1.4),Skinny,Flat Chest,Leaning Forward,Very Short Hair,Ponytail,(silver Tube Top,cyan Skirt:1.3),Yu-Gi-Oh,Priest ,(masterpiece,detailed,highres:1.4) <lora:contact:0.9>
Negative prompt
verybadimagenegative_v1.3, badhandv4, plain, minimal, gradient
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
74515189
Size
512x768
Clip skip
2
Prompt
best quality, intricate details, <lora:kson-06:0.8> kson(vshojo), belt, white footwear, black hair, black jacket, large breasts, coat, white pants, chest sarashi, simple background, cleavage, blue eyes, open clothes, pants, solo, black choker, boots, sarashi, midriff, green background, jacket, 1girl, looking at viewer, blue hair, ponytail, choker nebula background, space, stars, planets, darkness, <lora:contactStyle_v10Standard:0.8>
Negative prompt
(worst quality:1.4), (low quality:1.4), (monochrome:1.1), easynegative, bad-artist-anime, bad-image-v2-39000, bad_prompt_version2, bad_quality, ng_deepnegative_v1_75t, verybadimagenegative_v1.1-6400, vile_prompt3, bad-hands-5
Settings
Sampler
DDIM
Steps
30
Guidance
3
Seed
216313210
Size
768x1152
Clip skip
2
Prompt
girl, (detailed eyes),(mecha:1.4), Modern,Village Background,Pecs,Round Breasts,(Swimming),Very Short Hair,Braided Buns,(lilac Belted Top,turquoise Tapered Pants:1.3),Dragon Quest,Ribbon Choker ,(masterpiece,detailed,highres:1.4) <lora:contact:0.75>
Negative prompt
verybadimagenegative_v1.3, badhandv4, plain, minimal, gradient
Settings
Sampler
DDIM
Steps
30
Guidance
3
Seed
2201643402
Size
768x1152
Clip skip
2
Prompt
girl, (detailed eyes),(cat:1.4), Futuristic,Village Background,Plus Size,Big Breasts,(Running),Short Hair,Ponytail,(pink Bardot Top,tan Jeans:1.3),One Piece,Nail Polish ,(masterpiece,detailed,highres:1.4) <lora:contact:0.75>
Negative prompt
verybadimagenegative_v1.3, badhandv4, plain, minimal, gradient
Settings
Sampler
DDIM
Steps
30
Guidance
3
Seed
4128318371
Size
768x1152
Clip skip
2
Prompt
girl, (detailed eyes),(skeleton:1.4), New,Fight Background,Muscular,Busty,(Playing Sports),Long Hair,Bouffant,(beige Wrap Top,yellow Harem Pants:1.3),fate/grand order,Chinese Dress ,(masterpiece,detailed,highres:1.4) <lora:contact:0.75>
Negative prompt
verybadimagenegative_v1.3, badhandv4, plain, minimal, gradient
Settings
Sampler
DDIM
Steps
30
Guidance
8
Seed
150225635
Size
768x1152
Clip skip
2
Prompt
girl, (illustration:1.2), (Modern,Street Background:1.4),Pear Body,Big Breasts,Dynamic Pose,Very Long Hair,French Braid,(scarlet Belted Top,platinum Lace skirt:1.3),love live school idol project,Ribbon Choker ,(masterpiece,detailed,highres:1.4) <lora:contact:0.9>
Negative prompt
verybadimagenegative_v1.3, badhandv4, plain, minimal, gradient
Settings
Sampler
DDIM
Steps
30
Guidance
8
Seed
3513945395
Size
768x1152
Clip skip
2
Prompt
girl, (elf:1.2), (Flood,Nile Background:1.4),Skinny,Flat Breasts,Hand on shoulder,Very Short Hair,Fishtail Braids,(auburn Bralet Top,yellow Bodycon skirt:1.3),idolmaster,Pajamas ,(masterpiece,detailed,highres:1.4) <lora:contact:0.9>
Negative prompt
verybadimagenegative_v1.3, badhandv4, plain, minimal, gradient
Settings
Sampler
DDIM
Steps
30
Guidance
8
Seed
3026078588
Size
768x1152
Clip skip
2
Prompt
girl, (vector:1.2), (Futuristic,Bus Interior Background:1.4),Musclegut,Fat Breasts,Hugging Own Legs,Medium Hair,Pigtails,(saffron Cardigan,viridian Shorts:1.3),Pokemon,Sleeveless Dress ,(masterpiece,detailed,highres:1.4) <lora:contact:0.9>
Negative prompt
verybadimagenegative_v1.3, badhandv4, plain, minimal, gradient
AI Models for Image, Video & Text Generation
comics contact is a LoRA for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models