Update README.md

ed1e999 verified 6 months ago

1.32 kB

tags:
  - lora
  - diffusers
  - template:diffusion-lora
  - image-to-image
widget:
  - output:
      url: images/food.png
    text: Make Stereogram
  - output:
      url: images/bug.png
    text: Make Stereogram
  - output:
      url: images/3D.png
    text: Make Stereogram
  - output:
      url: images/foodm.png
    text: Make Stereogram
  - output:
      url: images/Human.png
    text: Make Stereogram
base_model: Qwen/Qwen-Image-Edit-2509
instance_prompt: Make Stereogram
license: mit
pipeline_tag: image-to-image

Qwen-Edit-2509-Stereogram_LoRa

Model description

The lora creates an second image that can be combined via image stich (with the orginal) to create an image that can be viewed in VR.

It works well with 3D, 2.5 and photos. 2D images can be an hit or miss, due to them missing in the dataset. Around 1700 images (16 Epochs) where used in the dataset, with mixed content. Works better then my Flux-Kontext-version.

Lower epochs can be found in the "epoch"-folder

I recommend generating atleast 2 imagepairs, with clip strength of 2 and model of 1.5 (varies for type of image and wanted effect depth)

Trigger words

You should use Make Stereogram to trigger the image generation.

Download model

Download them in the Files & versions tab.