Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
dark_v1.9-pony_done.safetensors
55 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<darker-images-xl>
About This Model
STABLE DIFFUSION XL 1.0 · LoRAs
Created by
psoft
on Civitai
by psoft - I've been trying to train a lora to achieve better dark images for quite a while, but was never satisfied with the results. The way SD works isn't ideal to be able to achieve this. This version, however, does produce good results. It works by combining some of the tags below and the weight of the lora. I recommend combining multiple tags from the list below. Note that the end result ultimately depends on the base model used.
Creator notes
Generate darker images for Halloween! You can support my work by posting your images here, by tipping Buzz, and by leaving a like if you enjoyed it! Get exclusive NSFW models at or . Follow for more! I've been trying to train a lora to achieve better dark images for quite a while, but was never satisfied with the results. The way SD works isn't ideal to be able to achieve this. This version, however, does produce good results. It works by combining some of the tags below and the weight of the lora. I recommend combining multiple tags from the list below. Note that the end result ultimately depends on the base model used. dark theme: general darker image dim lighting: darker image with dim light source black theme: darken image based on making things towards the black color, but it can lead to black and white results if there is no color tags in the prompt silhouette: darkens the character and tens to generate a rim light. I recommend using with the tag "solo" as it can generate silhouettes of others in the background dark dark room: similar to "dark background" black backlighting: generate the effect of light coming from behind the character, and it darken the character as well. I also tried to train with other tags, which you can try, but don't seem very effective: underlighting, sidelighting, uplighting, overlighting. Maybe for a future version I'll revisit this Other tags you can play with: shadow, shade, red light, blue light, red theme, blue theme. Recommended quality tags: score_9, score_8_up, score_7_up, score_6_up. Optional: source_anime Recommended negative tags: score_4, score_5. Optional: 3d, lips, realistic
Trigger words
dark theme
dim lighting
black theme
dark background
dark room
black background
silhouette
backlighting
8,464 downloads · 1,030 likes on Civitai
SHA256
40628F2DAC2AAFA6D51ED5257FC63A626BA06BF9CE45B32EF181AE7992C653D8
ModelTrends.ai Model ID
#5161
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
Euler a
Steps
25
Guidance
7
Seed
3114330730
Size
832x1216
Clip skip
2
Prompt
1girl, android, upper body, facing viewer, mechanical eyes, shaded face, glowing, dark theme, dim lighting, bioluminescent, mysterious, ethereal, vibrant colors, science fiction, future, (virtual:1.2), score_9, score_8_up, score_7_up, <lora:DunkingOnSouls_Soullify_v2.0:1>, <lora:dark_v1.9-pony:1>
Negative prompt
score_4, score_5, score_6, source_pony, source_furry, fewer digits, extra digits, polydactyly, (text, watermark, signature, sign, artist name, artist logo:1.8),
Settings
Sampler
Euler a
Steps
14
Guidance
3
Seed
1026574992
Size
832x1216
Clip skip
2
Weight used
0.5
Prompt
zPDXL3, DemizuPosuka, NLSTN,Dark Fantasy page,1girl, demon girl, succubus, horns, red skin, intricate glowing tattoos, wings, black hair, side braid, undercut, curvy, perfect face, looking at viewer, standing, medium breast, covered, gothic clothing, black clothing, midriff, skimpy clothing, dramatic pose, portrait, face focus, detailed face, red eyes, glowing eyes, neon, vibrant color, dynamic lighting, night, castle, dim lighting, [backlighting]
Negative prompt
negative_hand, cross, clothes, malformed hand, extra fingers
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
3867543785
Size
832x1216
Clip skip
2
Prompt
score_9, score_8_up, score_7_up, score_6_up, <lora:dark_v1.9-pony:1.0> black theme, dark theme, dark background, 1girl, long hair, blonde hair, looking at viewer, forest, night, jack-o'-lantern, witch, short dress, backlighting,
Negative prompt
score_4, score_5,
Settings
Sampler
Euler a
Steps
35
Guidance
7
Seed
1506064726
Size
832x1216
Clip skip
2
Weight used
1
Prompt
score_9, score_8_up, score_7_up, score_6_up, score_5_up, dynamic camera angle, 1girl, scene of a girl standing in a desert, BREAK, 1girl, cute 24 years, very long sandy hair, tails, medium breasts, hazel eyes, jean shorts, midriff, tight flannel shirt tied off below breasts, firm ass, hiking boots, standing in desert, surprised by overhead lights, gasping, BREAK, desert landscape, rocky, cactus, ((night, dim lighting)), single beam of bright green light shining down from heavens, girl transfixed by light, high definition, best quality, ultra detailed, 8k
Negative prompt
score_6, score_5, score_4, mutated hands, low res, blurry face, watermark, title, signature, NegativeDynamics, negative_hand, monochrome, teen, nudity, looking at viewer, looking into camera, very large snake, snake coiled around girl, cross eyed
Settings
Sampler
Euler a
Steps
38
Guidance
7
Seed
2124063946
Size
832x1216
Clip skip
2
Weight used
1
Prompt
score_9, score_8_up, score_7_up, score_6_up, ((solo, 1man, pale centaur, pale horse legs, skeletal torso, taur, pale fur, dark hooded figure, shadowy figure, Grim Reaper style, (faceless, blacked out face:1.2), raising one hoof)), lawful evil alignment, dungeons and dragons character, highly detailed, dnd, semi-realistic, IBG, intricately detailed, dramatic lighting, dark night, sharp edges, 8k resolution, wide shot, dark theme, dark aura, horror, spooky, occult, apocalyptic, nightmarish, silhouette, backlighting
Negative prompt
score_6, score_5, score_4, easynegative, creatures, (face, face on torso, horns on head, wings:1.5), background figures, sword, horse head, closed eyes, watermarks, text, signature, censored, anime, bad eyes, blurry eyes, worst quality, bad quality, jpeg artifacts, lowres, plain background
AI Models for Image, Video & Text Generation
darker images xl is a LoRA for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 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