import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Rempeyek/Woman_Cloth_XL")
prompt = "masterpiece, best quality, photorealistic, full body shot of a beautiful woman, wearing a classic little black dress, posing elegantly in a luxurious minimalist apartment, fashion photography, cinematic lighting."
image = pipe(prompt).images[0]Woman_Cloth_IL
.png)
- Prompt
- masterpiece, best quality, photorealistic, full body shot of a beautiful woman, wearing a classic little black dress, posing elegantly in a luxurious minimalist apartment, fashion photography, cinematic lighting.
- Negative Prompt
- EasyNegativeV2, fcNeg-neg, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (worst quality, low quality, normal quality:1.4), blurry, ugly, deformed, bad hands, bad anatomy, extra limbs, missing fingers, mutated hands, text, watermark, signature, username, jpeg artifacts, artist name, trademark, title
- Prompt
- masterpiece, best quality, 8k, edgy fashion look, beautiful woman, wearing a black mesh top over a bandeau, concert or festival setting.
- Negative Prompt
- EasyNegativeV2, fcNeg-neg, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (worst quality, low quality, normal quality:1.4), blurry, ugly, deformed, bad hands, bad anatomy, extra limbs, missing fingers, mutated hands, text, watermark, signature, username, jpeg artifacts, artist name, trademark, title
- Prompt
- masterpiece, best quality, photorealistic, beautiful woman, wearing a simple silk camisole, soft and casual indoor portrait.
- Negative Prompt
- EasyNegativeV2, fcNeg-neg, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (worst quality, low quality, normal quality:1.4), blurry, ugly, deformed, bad hands, bad anatomy, extra limbs, missing fingers, mutated hands, text, watermark, signature, username, jpeg artifacts, artist name, trademark, title
- Prompt
- masterpiece, best quality, sharp focus, beautiful woman, wearing a cute tie-front blouse, tropical beach setting. relaxed and happy.
- Negative Prompt
- EasyNegativeV2, fcNeg-neg, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (worst quality, low quality, normal quality:1.4), blurry, ugly, deformed, bad hands, bad anatomy, extra limbs, missing fingers, mutated hands, text, watermark, signature, username, jpeg artifacts, artist name, trademark, title
- Prompt
- masterpiece, best quality, photorealistic, beautiful woman, wearing a simple black tube top, casual summer look, city park background.
- Negative Prompt
- EasyNegativeV2, fcNeg-neg, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (worst quality, low quality, normal quality:1.4), blurry, ugly, deformed, bad hands, bad anatomy, extra limbs, missing fingers, mutated hands, text, watermark, signature, username, jpeg artifacts, artist name, trademark, title
- Prompt
- masterpiece, best quality, ultra-detailed, portrait of a beautiful woman, wearing a stylish halter neck summer dress, on a sunny beach, soft natural light.
- Negative Prompt
- EasyNegativeV2, fcNeg-neg, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (worst quality, low quality, normal quality:1.4), blurry, ugly, deformed, bad hands, bad anatomy, extra limbs, missing fingers, mutated hands, text, watermark, signature, username, jpeg artifacts, artist name, trademark, title
Model description
👗 Woman_Cloth_XL — SDXL LoRA v1.0
LoRA ini dilatih menggunakan Stable Diffusion XL (SDXL) dan difokuskan untuk menghasilkan berbagai gaya pakaian wanita — dari elegan hingga modern sexy. Cocok untuk visual fashion, illustrasi karakter, dan eksplorasi outfit.
🧠 Training Info
- Base Model: SDXL 1.0
- Resolution Dataset: 1024x1024
- Epochs: 10
- Batch Size: 4
- Network Rank/Dim: 8
- Alpha: 4
- Precision: fp16
- Scheduler: cosine_with_restarts
- Optimizer: AdamW8bit
- Trigger Token: `woman_cloth_xl`
🎯 Recommended Prompt
```text (masterpiece, best quality), woman_cloth_xl, modern outfit, full body, ultra detailed, standing in natural light
Trigger words
You should use woman_cloth_xl to trigger the image generation.
You should use cloth to trigger the image generation.
You should use crop top to trigger the image generation.
You should use mash to trigger the image generation.
You should use dress to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 4
Model tree for Rempeyek/Woman_Cloth_XL
Base model
stabilityai/stable-diffusion-xl-base-1.0