Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
closeupface-v1.1.safetensors
308 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<face-portraits-huny>
About This Model
HUNYUAN · LoRAs
Created by
jhnprst2150
on Civitai
by jhnprst2150 - Prompt example : A closeup on the cheek and nose of a sexy female, we can see eyelashes and eyebrows very close. Skin pores and some blemishes are clearly visible. The camera zooms out quickly to show her mouth with kissing lips, then opening wide to a smile showing teeth.
Creator notes
Trained on 200+ very highly detailed high resolution (min 2000px) images + 35 hires vidclips of amateur female face portraits, with visible skin pores, skin hairs and blemishes/moles. The lora is intended to use for higher resolutions like 768px and up (width and/or height) - as training concentrated image and vidframes samples between 768 and 1152px this is where performs best. My samples posted are made with DPM++2M, Scheduler Beta for 28 steps on the original tencent bf16 models at 512x768 resolution frames, lora strength 0.85. The quants/fpX/fastvid I tried all produced visible different and degraded quality IMHO. V1.1 works better with other Loras - put it around 3/4 weight of the other Lora; e.g. this Lora at 0.65, the other Lora (character etc.) at 0.9 For SkyReels or Hunyuan ImageToVideo vids, lower the strength to about 0.4 for vids over 73 frames. the Lora was only trained on snippets <73 frames, and this seems to have more visible (anti)effect on longer vids based on I2V model than T2V.
5,282 downloads · 286 likes on Civitai
SHA256
1C21DFFD1A476E2B71C1215602FACEF8C0F0550B7AF8C7869FFEF69CCC1C67DA
ModelTrends.ai Model ID
#8138
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
Steps
40
Guidance
6
Size
1600x1408
Prompt
a realistic slow motion scene. an alien gray taking a selfie with his phone and showing the peace sign with his other hand. behind him far away a cow is floating upwards to an floating flying saucer ,ultra realistic photo, cinematic scene. realistic style, slow movements camera slowly circles around
Settings
Size
768x1152
Prompt
closeup of a open mouth of a woman with clear detail of the skin's texture. she is pickle in her mouth, the tounge is out surrounding the pickle. the pickle's surface has very tranparent shiny reflecting wet liquid on it. The messy hair adds character to the scene, background is slightly out of focus, natural light gently highlights the subjects natural lighting, cinematic video, ultra-highres, highres, 4k, realistic, absurdres, masterpiece, photorealistic
Settings
Steps
40
Guidance
6
Size
1408x1792
Prompt
A slow dynamic depiction of Chun-Li, the iconic Street Fighter character, showcasing her muscular physique and intense determination.with a huge cleavage and a wet cameltoe and brown hair and green eyes. Chun-Li, a female character instantly recognizable from the Street Fighter video game series. She is depicted in a powerful pose. Her leg is sharply extended, revealing detailed musculature highlighted by sweat droplets suggesting intense physical exertion. Her expression is fierce and focused; her brow is slightly furrowed, and her eyes reflect determination.her hair is wet, water droplets run down her body and face. Chun-Li is wearing her signature blue qipao-style dress, which is intricately detailed with gold-colored designs. The dress clings to her muscular physique, accentuating her powerful build. She wears brown tights underneath. A white sash is tied around her high bun, adding to her classic look. She has pearl earrings, her knuckles are clenched, and she sports a spiked wristband on her right wrist and she wears white boots. the background is a crowded city with a wet street and a cheering crowd. the weather is shiny and bright with some clouds. cinematron realistic style
Settings
Steps
40
Guidance
6
Size
1792x1408
Prompt
The scene is portraying Darth Vader and Padme Amidala in an intimate embrace. Darth Vader, his iconic black helmet gleaming, is shown from the waist up, his dark, imposing presence softened by the tenderness of his embrace. His gloved hands gently hold Padme's Natlie Portman pOrtm4n waist and arm. The detail on his suit is visible, including the utility belt with its illuminated compartments. His cape falls dramatically behind him. Padme Amidala played by natalie portman pOrtm4n,with bright brown eyes and a beautiful face, depicted in a flowing, elegant white gown with long sleeves and a cape-like train, is shown in profile, her face turned towards Darth Vader's helmet. Her expression is one of serene devotion, her eyes closed as if lost in the moment. Her brown hair is neatly pulled back into a bun. She wears a simple silver bracelet on her left wrist. Her posture is graceful, and her body language conveys vulnerability and trust despite the formidable presence of her partner. The background is purposely dark and moody, dominated by deep shadows and rays of warm, blue light. grand hall and temple, which adds to the drama and intensity of the scene. The overall atmosphere is a poignant mix of love and danger, darkness and light. The contrast between Vader's dark attire and Padme's light-colored dress enhances this duality. The overall mood is one of bittersweet romance, highlighting an unlikely pairing full of complex emotions and unresolved conflict. The artist's style is highly detailed and realistic, focusing on the characters' expressions and textures to convey the narrative effectively. cinematron (((realistic style)))
AI Models for Image, Video & Text Generation
face portraits huny is a LoRA for the Hunyuan family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Hunyuan 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