README.md

metadata

tags:
  - text-to-image
  - flux
  - lora
  - diffusers
  - template:sd-lora
  - ai-toolkit
widget:
  - text: '[trigger] holding a sign that says ''I LOVE PROMPTS!'''
    output:
      url: samples/1726292433854__000002000_0.jpg
  - text: >-
      [trigger] santa clause holding a bottle of face serum. bottle label
      contains text "Salicylic Acid 02% FACE SERUM with oligopeptide-10 egcg +
      horehound extract reduces oil, acne, blackheads for acne prone skin
      30m1/1floz Minimalist"
    output:
      url: samples/1726292447101__000002000_1.jpg
  - text: >-
      [trigger] A woman holding news papper, sitting at a cafe. Newspaper
      contains text "Earnings from export of basmati had fallen sharply due to
      trade restrictions, while onion growers and traders had demanded removal
      of export barriers. The Centre on Friday scrapped the minimum export
      prices (MEPs) on basmati and onion it had imposed last year to cool
      domestic food inflation, according to separate notifications, in steps
      that will cheer farmers and traders." This is in small text, but readable
    output:
      url: samples/1726292460370__000002000_2.jpg
  - text: >-
      [trigger] A IT service center advertisement that contains text "Jeswin IT
      services. Reliable Solutions for All Your Tech Troubles! • Virus removal
      and system security • Hardware repairs and upgrades • Data recovery and
      backup solutions"
    output:
      url: samples/1726292473636__000002000_3.jpg
  - text: >-
      [trigger] A film ad that contains the heros and heroins image and the text
      "From visionary director James Cameron comes an epic adventure that will
      push the boundaries of cinema... AQUATERRA Starring: Chris Hemsworth"
    output:
      url: samples/1726292486923__000002000_4.jpg
  - text: >-
      [trigger] A circus company ad that contains  the text "Prepare to be
      amazed, astounded, and enchanted by the wonders of Cirque Magnifique!"
    output:
      url: samples/1726292500195__000002000_5.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: p3r5on
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

flux_lora_text2

Model trained with AI Toolkit by Ostris

Prompt

[trigger] holding a sign that says 'I LOVE PROMPTS!'

Prompt

[trigger] santa clause holding a bottle of face serum. bottle label contains text "Salicylic Acid 02% FACE SERUM with oligopeptide-10 egcg + horehound extract reduces oil, acne, blackheads for acne prone skin 30m1/1floz Minimalist"

Prompt

[trigger] A woman holding news papper, sitting at a cafe. Newspaper contains text "Earnings from export of basmati had fallen sharply due to trade restrictions, while onion growers and traders had demanded removal of export barriers. The Centre on Friday scrapped the minimum export prices (MEPs) on basmati and onion it had imposed last year to cool domestic food inflation, according to separate notifications, in steps that will cheer farmers and traders." This is in small text, but readable

Prompt

[trigger] A IT service center advertisement that contains text "Jeswin IT services. Reliable Solutions for All Your Tech Troubles! • Virus removal and system security • Hardware repairs and upgrades • Data recovery and backup solutions"

Prompt

[trigger] A film ad that contains the heros and heroins image and the text "From visionary director James Cameron comes an epic adventure that will push the boundaries of cinema... AQUATERRA Starring: Chris Hemsworth"

Prompt

[trigger] A circus company ad that contains the text "Prepare to be amazed, astounded, and enchanted by the wonders of Cirque Magnifique!"

Trigger words

You should use p3r5on 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('jcyriac/flux_lora_text2', weight_name='flux_lora_text2')
image = pipeline('[trigger] holding a sign that says 'I LOVE PROMPTS!'').images[0]
image.save("my_image.png")

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