metadata
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
- text: A woman wearing a saree in a white living room
output:
url: samples/1728503599653__000001000_0.jpg
- text: >-
A woman wearing a saree GHMSJK standing stylishly in front of an empty
cafe in pairs
output:
url: samples/1728503623163__000001000_1.jpg
- text: >-
The image features a woman wearing a vibrant yellow saree with intricate
floral embroidery. The saree is adorned with a variety of flowers in
shades of pink, orange, and green, creating a lively and colorful pattern.
The border of the saree is embellished with small, delicate beads and
sequins, adding a touch of sparkle. The saree is draped elegantly, with
the pallu (the end of the saree) flowing gracefully. The woman is standing
in a side profile, allowing a clear view of the saree's design and
detailing. The background is a neutral, textured wall, which contrasts
with the bright colors of the saree, making it stand out. The camera angle
is slightly elevated, capturing the full length of the saree and the
person's upper body. The overall composition highlights the intricate
craftsmanship and vibrant colors of the saree. GHMSJK
output:
url: samples/1728503646691__000001000_2.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: GHMSJK
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
ad-saree-2
Model trained with AI Toolkit by Ostris
Trigger words
You should use GHMSJK
to trigger the image generation.
Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('histin116/ad-saree-2', weight_name='ad-saree-2.safetensors')
image = pipeline('A woman wearing a saree in a white living room').images[0]
image.save("my_image.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers