metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- 3D
- Emojies
widget:
- text: >-
3D Emojies, An animated head of a woman with brown hair and a purple crown
on her head that says "LIVE" in white letters. The head is facing towards
the left side of the image. Her eyes are blue and her mouth is slightly
open. She is wearing a headset that is white and has a blue microphone
attached to it. The background is a vibrant purple color.
output:
url: images/1.png
- text: >-
3D Emojies, a vibrant orange face is adorned with the words "VIBES" and
"BAD" written on it in black marker. Above the face, a head of a black
rabbit is seen, adorned with five yellow bananas, adding a pop of color to
the scene. The background is a stark white, creating a stark contrast to
the orange face.
output:
url: images/2.png
- text: >-
3D Emojies, a 3D rendering of a mans face features a black mustache and
googles. The mans head is adorned with a beige beanie, adorned with black
eyebrows and black circles. The background is a creamy beige, adding a pop
of color to the scene.
output:
url: images/3.png
- text: >-
3D Emojies, Captured from a high-angle perspective on a pink backdrop, a
cartoon face is adorned with a purple mustache and black rimmed glasses.
The eyes, a pink nose, and a black beanie cap are adorned with purple
circles. The background is a soft pink, adding a pop of color to the
scene.
output:
url: images/4.png
- text: >-
3D Emojies, a cheerful orange cat face wearing oversized pink sunglasses
with heart-shaped lenses. Its whiskers are white, and its ears are tipped
with a gradient of blue. The cats mouth is wide open in a smile, showing
tiny white teeth. The background is a vibrant teal, giving the scene a
playful and summery vibe.
output:
url: images/5.png
- text: >-
3D Emojies, a cheerful sun with a smiling face, wearing round glasses with
rainbow-colored lenses. Its rays are wavy and multi-colored, giving it a
whimsical appearance. The background is a clear blue sky with birds flying
in the distance.
output:
url: images/6.png
- text: >-
3D Emojies, a cheerful sun with a smiling face, wearing round glasses with
rainbow-colored lenses. Its rays are wavy and multi-colored, giving it a
whimsical appearance. The background is a clear blue sky with birds flying
in the distance.
output:
url: images/7.png
- text: >-
3D Emojies, a playful clown face with a bright red nose, curly blue hair,
and a yellow party hat covered in polka dots. The clowns face is painted
with a happy expression, including exaggerated black eyebrows and a big
toothy grin. The background is a carnival scene with balloons and
confetti.
output:
url: images/8.png
- text: >-
3D Emojies, a golden retriever puppy face wearing a pair of aviator
sunglasses. The puppys tongue is hanging out, and it has a blue bandana
tied around its neck. The background is a sunny beach scene with waves and
palm trees in the distance.
output:
url: images/9.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: 3D Emojies
license: creativeml-openrail-m
Model description for Flux-3D-Emojies-LoRA
Image Processing Parameters
Parameter | Value | Parameter | Value |
---|---|---|---|
LR Scheduler | constant | Noise Offset | 0.03 |
Optimizer | AdamW | Multires Noise Discount | 0.1 |
Network Dim | 64 | Multires Noise Iterations | 10 |
Network Alpha | 32 | Repeat & Steps | 24 & 3250 |
Epoch | 18 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 24 [ Flat 4K ]
Best Dimensions & Inference
Dimensions | Aspect Ratio | Recommendation |
---|---|---|
1280 x 832 | 3:2 | Best |
1024 x 1024 | 1:1 | Default |
Inference Range
- Recommended Inference Steps: 30–35
Setting Up
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Flux-3D-Emojies-LoRA"
trigger_word = "3D Emojies"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use 3D Emojies
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.