metadata

tags:
  - text-to-image
  - flux
  - lora
  - diffusers
  - template:sd-lora
  - fluxgym
widget:
  - output:
      url: sample/ldlaughingmemeface_000450_00_20241001223402.png
    text: >-
      LDME Young adult male at a party, mid-laugh with eyebrows raised in mock
      surprise. He's holding a red solo cup and wearing a graphic t-shirt
  - output:
      url: sample/ldlaughingmemeface_000450_01_20241001223612.png
    text: >-
      LDME Close-up of a smirking businessman with arched eyebrows, squinting
      eyes, and a slightly open mouth. He's holding a coffee mug in an office
      setting
  - output:
      url: sample/ldlaughingmemeface_000450_02_20241001223822.png
    text: >-
      LDME middle-aged woman in a casual shirt, raising his eyebrows skeptically
      while holding a martini
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: LDME
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

LDLaughingMemeFace

A Flux LoRA trained on a local computer with Fluxgym

Prompt
LDME Young adult male at a party, mid-laugh with eyebrows raised in mock surprise. He's holding a red solo cup and wearing a graphic t-shirt

Prompt
LDME Close-up of a smirking businessman with arched eyebrows, squinting eyes, and a slightly open mouth. He's holding a coffee mug in an office setting

Prompt
LDME middle-aged woman in a casual shirt, raising his eyebrows skeptically while holding a martini

Prompt
LDME a man at a theme park, holding an oversized stuffed animal prize with a smirk and raised eyebrows, as if mocking the absurdity of his win

Prompt
LDME a man in the kitchen, holding a burnt piece of toast with eyebrows raised and mouth agape, as if questioning how he managed to mess up breakfast so spectacularly

Trigger words

You should use LDME to trigger the image generation.

How to Use This LoRA Model

Describing the Expression

To get the best results from this LoRA model, use descriptive words that capture the essence of the facial expressions you want to generate. Consider phrases like:

"exaggerated expression" "raised eyebrows" "as if mocking" "eyebrows lifted and smirking"

These descriptors will help the model focus on creating the unique, expressive faces you're aiming for.

Adjusting LoRA Strength

Strength 1: At full strength, the LoRA model tends to generate images of the same character when you prompt with "a man." This can be useful if you want consistency in character appearance.

Dialing Down Strength: If you wish to create different characters or add variety, reduce the strength of the LoRA. A strength setting around 0.7 has been effective for me, but I encourage experimenting with different levels to achieve your desired outcome.

Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.

Weights for this model are available in Safetensors format.