Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
howlbgsv3.safetensors
144 MB · SafeTensor · fp16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<howls-style>
About This Model
STABLE DIFFUSION 1.5 · LoRAs
Created by
nucleardiffusion
on Civitai
Creator notes
v3 - Updated methods, accuracy, captions and a bunch of other work over a few days. Though similar results, I feel this version prompts better now; Examples are with the preview images but it tends to work well even just written as: or: in the style of , It can be tricky to get night scenes ( especially indoors ) this is something I might improve in the future but for now try adding night, dark, to prompts. FOR v2 USERS: you no longer need howlsbgs as a trigger word on v3. or please consider an easy one off donation here: Trained from the brilliant Ghibli movie Howls Moving Castle only, this LoRA is capable of creating different interiors and landscapes in the style from the film. Notice: This free work is intended for art and illustration purposes of emergent technology and not intended nor' trained for making illicit images, as the author I've taken care to not use any private data in the training process or designed it for such purposes. By downloading this model you are agreeing with the aforementioned intent and that you will not use my work to create / share images of a potentially immoral and / or illegal nature.
33,410 downloads · 5,539 likes on Civitai
SHA256
3F9B3E7F43E42253622A53BD0AEBA0F3942D13C4FC6ED90282B93D0112544F57
ModelTrends.ai Model ID
#206
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
DPM++ SDE Karras
Steps
30
Guidance
7
Seed
3366139121
Size
768x512
Prompt
in the style of <lora:howllatentDADAP4:1> , scenery
Negative prompt
EasyNegative
Settings
Sampler
Euler a
Steps
20
Guidance
6
Seed
2073657573
Size
720x1024
Prompt
<lora:ghibli_style_offset:0.7> ghibli style , 1female, blonde hair, long hair, wavy hair, kimono <lora:howllatentDADAP4:0.6> howlbg, lake, koi fish
Negative prompt
badhandv4 easynegative
Settings
Sampler
DPM++ SDE Karras
Steps
30
Guidance
7
Seed
3430806169
Size
768x512
Prompt
in the style of <lora:howllatentDADAP4:1> , old house, inside, sunlit, lamp,
Negative prompt
EasyNegative
Settings
Sampler
DPM++ SDE Karras
Steps
30
Guidance
7
Seed
1333540937
Size
768x512
Prompt
in the style of <lora:howllatentDADAP4:1>, night, landscape,
Negative prompt
EasyNegative
Settings
Sampler
DPM++ 2M Karras
Steps
32
Guidance
8.5
Seed
243161887
Size
856x480
Clip skip
2
Prompt
Ghibli Style, pipes <lora:howlbgs:0.3>, <lora:studioGhibliStyle_offset:0.5>
Negative prompt
EasyNegative, hand
Settings
Sampler
DPM++ 2M
Steps
40
Guidance
7
Seed
3554567230
Size
1536x1536
Clip skip
2
Prompt
masterpiece,absurdres,high res,best quality,<lora:uv:1.2>,blacklight,ultra_detailed,intricate,scenery,masterpiece, best quality, highres, absurdres,landscape,a painting of a cave with a lot of trees and plants and ruins and light comming inside, concept art , matte fantasy painting, a detailed matte painting, fantasy art,no_humans, Create sharp defined light with a soft glow,Create long narrow light sources for dramatic lighting effects,Add color to the light and create a haunting mood and a ominous atmosphere,extremely detailed, extremely detailed textures,Wide-angle lens,<lora:LowRA:0.6>, <lora:epiNoiseoffset_v2:0.6>,scenery,absurdres,mountains,at night, Eyvind Earle, a detailed matte painting, fantasy art,<lora:epiNoiseoffset_v2:0.5>, <lora:howlbgsv3:0.5>, <lora:artbytokiame:0.5>, <lora:add_detail:0.4>, ink outlines, wallpaper, vignette, matte painting,complex lighting, dynamic shading, complementary colors, HDR, absurdres, cinematic, saturated colors, flat color pallete, (masterpiece:1.2), (best quality:1.1),BREAK
Negative prompt
1girl,1boy,character,multiple_girls,multiple_others,multiple_boys,FastNegativeV2,By bad artist -neg, EasyNegative,bad_quality,worst_quality,blurry, blurry_background, blurry_foreground,bad_artist, (bad_prompt_version2:0.8), sketch, lowres, text, error, cropped, worst_quality, low_quality, normal_quality, jpeg_artifacts, signature, watermark, username, blurry, artist_name, kitsch, ugly, disgusting, poorly_drawn, childish, lowres, text, error, cropped, worst_quality, low_quality, normal_quality, jpeg_artifacts, signature, watermark, username, blurry, lowres, blurry_text, out_of_frame, cropped,signature, watermark, username, artist_name,sketch,incomplete,work_in_progress, (worst quality:2), (low quality:2), (normal quality:2)
Settings
Sampler
DPM++ SDE Karras
Steps
30
Guidance
7
Seed
1746522635
Size
768x512
Prompt
in the style of <lora:howllatentDADAP4:1> , scenery, night, town
Negative prompt
EasyNegative
AI Models for Image, Video & Text Generation
howls style 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