Run Locally
Expressions_Helper.safetensors
36 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION 1.5 · LoRAs
__html__Expressions Helper Realistic is the outcome of an ambitious project that focuses on capturing real facial expressions. Trained for 10 epochs and 3830 steps, this AI model utilizes images from films and photographs of real individuals to help generate authentic expressions of disgust, surprise, sadness, anger, and fear. The model's weights vary for each expression and the models used, while the results are influenced by both positive and negative prompts. With its advanced algorithms and training, Expressions Helper Realistic Model offers a valuable tool to facilitate the creation of realistic and emotionally rich facial expressions, enhancing storytelling and creative projects.The keyword is recommended to be inserted at the beginning of the prompt to have a more effective effectKeywords :angrysadsurprisedscareddisgustedWith unrealistic styles the result is not guaranteed because the model has been trained only with realistic images, although this works more or less effectively on all styles. Just try it!
Creator notes
Expressions Helper Realistic is the outcome of an ambitious project that focuses on capturing real facial expressions. Trained for 10 epochs and 3830 steps, this AI model utilizes images from films and photographs of real individuals to help generate authentic expressions of disgust, surprise, sadness, anger, and fear. The model's weights vary for each expression and the models used, while the results are influenced by both positive and negative prompts. With its advanced algorithms and training, Expressions Helper Realistic Model offers a valuable tool to facilitate the creation of realistic and emotionally rich facial expressions, enhancing storytelling and creative projects.
The keyword is recommended to be inserted at the beginning of the prompt to have a more effective effect
Keywords :
-
angry
-
sad
-
surprised
-
scared
-
disgusted
With unrealistic styles the result is not guaranteed because the model has been trained only with realistic images, although this works more or less effectively on all styles.
Just try it!
Trigger words
disgusted
angry
sad
surprised
scared
SHA256
6C72DFEAC23A1EA3750628E045D55AC62843B078178973DAC316EDF9E3257E42
ModelTrends.ai Model ID
#12749
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++ 2M
Steps
30
Guidance
7
Seed
156516779
Size
896x1152
Clip skip
2
Prompt
<lora:InCase-LyCoris-V4:1> <lora:Incase [MockAi - v1.0]:1> <lora:concept-expression_chart-v1:1> <lora:princess_xl_v2:1> <lora:more_details:1>, <lora:dare_cosplay_selfie:1>, <lora:Expressions_Helper:1>, <lora:Pony_QualityV4.0:1>
Negative prompt
EasyNegative ImgFixerPre0.3
Settings
Sampler
DPM++ 2M
Steps
30
Guidance
7
Seed
2290503749
Size
896x1152
Clip skip
2
Prompt
<lora:InCase-LyCoris-V4:1> <lora:Incase [MockAi - v1.0]:1> <lora:concept-expression_chart-v1:1> <lora:princess_xl_v2:1> <lora:more_details:1>, <lora:dare_cosplay_selfie:1>, <lora:Expressions_Helper:1>, <lora:Pony_QualityV4.0:1>
Negative prompt
EasyNegative ImgFixerPre0.3
Settings
Sampler
DPM++ 2M
Steps
30
Guidance
7
Seed
4012706131
Size
896x1152
Clip skip
2
Prompt
<lora:InCase-LyCoris-V4:1> <lora:Incase [MockAi - v1.0]:1> <lora:concept-expression_chart-v1:1> <lora:princess_xl_v2:1> <lora:more_details:1>, <lora:dare_cosplay_selfie:1>, <lora:Expressions_Helper:1>, <lora:Pony_QualityV4.0:1>
Negative prompt
EasyNegative ImgFixerPre0.3
Settings
Sampler
Euler a
Steps
20
Guidance
7
Seed
217005883
Size
512x512
Prompt
( disgusted ), photo portrait of a man with a beard and orange glasses wearing a hat, fashion photography
Settings
Sampler
DPM++ 2M
Steps
40
Guidance
7
Seed
1251809440
Size
512x1024
Clip skip
2
Prompt
(((SFW))), ((fully dressed:1.2)), censored, masterpiece, extreme details, detailed, focus, realistic, photorealistic, 4k, 8k, 16k, highres, (absurdly high resolution:1.4), <lora:BRBrunette:1>, ((pale skin)), medium breast, long black hair, blue eyes, <lora:epiCRealLife:0.7>, 1girl, (<lora:Expressions_Helper:0.6>,<lora:emotional:2>, Teasing, A playful smirk, a raised eyebrow, and a hint of dominance:1.2), (makeup bright neon avant-garde red eyeshadow, thick pink dotted Swarovski eyeliner, long pink lashes, glossy lipstick), RandomPoses, views, high-neck long dress, <lora:BS:0.8>, In a plaza with the Notre-Dame Cathedral in the background <lora:Beautiful outdoor-Countryside:0.65>
Negative prompt
EasyNegativeV2,badhandv4, Simple BackGround, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, normal quality, ((monochrome)), ((grayscale)), (extra fingers, deformed hands, polydactyl:1.5), wrong finger, bad hands, missing fingers, mutated hands, poorly drawn hands, blurry, text, logo, jpeg artifacts, signature, watermark, username, ((monochrome)), Paintings, sketches, skin spots, acnes, skin blemishes, age spot, strabismus, poorly drawn face, ugly face, deformed face,malformed face, bad anatomy, bad feet, ugly, pregnant, duplicate, morbid, mutilated, long neck, mutation, deformed chest, bad proportions, malformed limbs, extra limbs, cloned face, disfigured, gross proportions, (missing arms:1.331), (missing legs:1.331), (extra arms:1.331), (extra legs:1.331), bad legs, pubic hair, ((bad art)), extra head,
Settings
Sampler
DPM++ 2M
Steps
40
Guidance
7
Seed
1048300388
Size
512x1024
Clip skip
2
Prompt
(((SFW))), ((fully dressed:1.2)), censored, masterpiece, extreme details, detailed, focus, realistic, photorealistic, 4k, 8k, 16k, highres, (absurdly high resolution:1.4), <lora:BRBrunette:1.1>, goth makeup, (black lipstick:1.3), pale skin, medium breast, long hair, black hair, blue eyes, choker, <lora:epiCRealLife:0.7>, 1girl, <lora:edgFantasy_Dress:0.2>,<lora:FantasyRobes-10:1>, <lora:more_details:0.15>, Wearing Frostbound Iceweaver Robes with Glacial Crystals, icy tiara, (<lora:Expressions_Helper:0.6>,<lora:emotional:2>, Seductive, A sultry gaze, a slightly parted lips, and a hint of a smile:1.2), (makeup bright neon dotted hearts avant-garde shimmering red eyeshadow, thick black eyeliner, shimmering lipstick), <lora:FantasyUnderground-10:0.4>,<lora:Ghibli_v6:0.4>, In the Luminous Grove bathed in Eternal Moonlight, (full body portrait:1.2), ((from behind, view from side angle, side angle view)), Thumbs up
Negative prompt
EasyNegativeV2,badhandv4, Simple BackGround, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, normal quality, ((monochrome)), ((grayscale)), (extra fingers, deformed hands, polydactyl:1.5), wrong finger, bad hands, missing fingers, mutated hands, poorly drawn hands, blurry, text, logo, jpeg artifacts, signature, watermark, username, ((monochrome)), Paintings, sketches, skin spots, acnes, skin blemishes, age spot, strabismus, poorly drawn face, ugly face, deformed face,malformed face, bad anatomy, bad feet, ugly, pregnant, duplicate, morbid, mutilated, long neck, mutation, deformed chest, bad proportions, malformed limbs, extra limbs, cloned face, disfigured, gross proportions, (missing arms:1.331), (missing legs:1.331), (extra arms:1.331), (extra legs:1.331), bad legs, pubic hair, ((bad art)), extra head,
Settings
Sampler
LCM
Steps
6
Guidance
1
Seed
1486870343
Size
512x512
Clip skip
2
Weight used
1
Prompt
a sexy police woman, dirty blonde, gorgeous face, short hair, skin tight uniform, curvaceous,, intense look in eyes, resting bitch face, posing,
Negative prompt
negative_hand
Similar Models
AI Models for Image, Video & Text Generation
expressions helper 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.
More Stable Diffusion 1.5 modelsMore Stable Diffusion 1.5 LoRAsrealisticexpressionsobjectsconceptshelperinpaintingportraits
Browse by Model Family
Text / LLM Models
415
Anima Models
519
Chroma Models
15
Flux Models
1,497
Flux 2 / Klein Models
1,239
MiniMax H3 Models
332
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
677
Qwen Models
20
Qwen2 Models
37
Ltx2 Models
152
Stable Diffusion 1.5 Models
7,032
Stable Diffusion XL 1.0 Models
17,383
Zimage Models
815
Wan Models
1,244

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
All Rights Reserved
