metadata

tags:
  - text-to-image
  - flux
  - lora
  - diffusers
  - template:sd-lora
  - ai-toolkit
widget:
  - text: An ornate green faberge egg faberge_egg
    output:
      url: samples/1733410745801__000001000_0.jpg
  - text: A royal red faberge egg with gold highlights on a sturdy base faberge_egg
    output:
      url: samples/1733410764369__000001000_1.jpg
  - text: Four differently-styled unique faberge eggs next to each other faberge_egg
    output:
      url: samples/1733410782939__000001000_2.jpg
  - text: >-
      Four faberge eggs next to each other on a wooden desk. Each egg is a
      different color than the others. Each egg is of a completely different
      style than the others. faberge_egg
    output:
      url: images/example_pahmsogiv.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: faberge_egg
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

fabergeegg

Model trained with AI Toolkit by Ostris

Prompt
A royal red faberge egg with gold highlights on a sturdy base faberge_egg

Prompt
Four differently-styled unique faberge eggs next to each other faberge_egg

Prompt
Four faberge eggs next to each other on a wooden desk. Each egg is a different color than the others. Each egg is of a completely different style than the others. faberge_egg

Trigger words

You should use faberge_egg 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('sohvren/fabergeegg', weight_name='fabergeegg.safetensors')
image = pipeline('An ornate green faberge egg faberge_egg').images[0]
image.save("my_image.png")

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers