phucleh2's picture
Update README.md
d9ad63d
|
raw
history blame
1.65 kB
metadata
base_model: runwayml/stable-diffusion-v1-5
tags:
  - controlnet
  - stable-diffusion
  - image-to-image
  - mask-to-cloth
language:
  - en
library_name: diffusers
widget:
  - src: >-
      https://huggingface.co/phucleh2/controlnet_mask2cloth/resolve/main/Examples/mask1.jpg
    prompt: a red top with a lace - trimmed neckline
  - src: >-
      https://huggingface.co/phucleh2/controlnet_mask2cloth/resolve/main/Examples/mask2.jpg
    prompt: a long sleeved top - black
  - src: >-
      https://huggingface.co/phucleh2/controlnet_mask2cloth/resolve/main/Examples/mask3.jpg
    prompt: a blue blouse with a tie neck and a floral prints
  - src: >-
      https://huggingface.co/phucleh2/controlnet_mask2cloth/resolve/main/Examples/mask4.jpg
    prompt: a light pink blouse with rose patterns
  - src: >-
      https://huggingface.co/phucleh2/controlnet_mask2cloth/resolve/main/Examples/mask5.jpg
    prompt: t-shirt - black

Mask + Prompt → Cloth

  • This model is still in development for better realistic-ness of the output. Stay tuned 🤗
  • This model is a fine-tuned version of ControlNet, tailored to utilize a black-and-white outline of an upper garment (mask) and a descriptive prompt to generate a garment that aligns with the mask's outline.
  • It's important to note that this model exclusively operates with upper garments. Please refrain from inputting masks for pants or jeans, as this could yield unexpected outcomes.
  • Input mask size: 384 x 512
  • Each time the model is executed, even with the same mask and prompt, it will generate a distinct output.
  • This model is a fine-tuned of ControlNet using VITON-HD dataset