Update README.md

269e1e4 verified 26 days ago

4.69 kB

tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - output:
      url: images/ComfyUI_temp_bgxgv_00027_.png
    text: >-
      a white yeti with horns reading a book that is titled "Ostris + Krea2
      Style Reference"
  - output:
      url: images/ComfyUI_temp_bgxgv_00030_.png
    text: >-
      a white yeti with horns reading a book that is titled "Ostris + Krea2
      Style Reference"
  - output:
      url: images/ComfyUI_temp_bgxgv_00028_.png
    text: >-
      a white yeti with horns reading a book that is titled "Ostris + Krea2
      Style Reference"
  - output:
      url: images/ComfyUI_temp_bgxgv_00031_.png
    text: >-
      a white yeti with horns reading a book that is titled "Ostris + Krea2
      Style Reference"
  - output:
      url: images/ComfyUI_temp_bgxgv_00062_.png
    text: >-
      a white yeti with horns reading a book that is titled "Ostris + Krea2
      Style Reference"
  - output:
      url: images/ComfyUI_temp_bgxgv_00068_.png
    text: >-
      a white yeti with horns reading a book that is titled "Ostris + Krea2
      Style Reference"
license: other
license_name: krea-2-community-license
license_link: https://huggingface.co/krea/Krea-2-Turbo/blob/main/LICENSE.pdf
base_model: krea/Krea-2-Turbo
instance_prompt: null

Krea 2 Style Reference LoRA

Prompt

a white yeti with horns reading a book that is titled "Ostris + Krea2 Style Reference"

Model description

This LoRA will allow you to inference on the Krea2 Turbo model in the style of a reference image. It was trained with AI Toolkit using the experimental Krea2 reference image trainer with the turbo training adapter. It was trained on thousands of hand curated style pairs I have been building over the years. It was trained to handle 1-2 reference images.

For inference in Comfy UI you will need this custom node. ComfyUI-Krea2-Ostris-Edit Use the template in that repo with this lora for the effect. No trigger word is needed just image and prompt.

For diffusers, there is a communiuty pipeline here ostris/Krea2OstrisEdit. You can run it like below:

import torch
from diffusers import DiffusionPipeline
from PIL import Image

pipe = DiffusionPipeline.from_pretrained(
    "krea/Krea-2-Turbo",
    custom_pipeline="ostris/Krea2OstrisEdit",
    torch_dtype=torch.bfloat16,
)
pipe.enable_model_cpu_offload()  # or pipe.to("cuda") with ~40+ GB of VRAM

# An AI-Toolkit Krea 2 LoRA, e.g. the style reference LoRA
pipe.load_lora_weights(
    "ostris/krea2_turbo_style_reference", weight_name="krea2_style_reference.safetensors"
)

image = pipe(
    "a white yeti with horns reading a book",
    image=Image.open("style_reference.png"),  # one reference image or a list of them
).images[0]
image.save("output.png")

Download model

Download them in the Files & versions tab.