metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Claymation
widget:
- text: >-
Claymation, Captured from a high-angle perspective on a vibrant yellow
backdrop, a medium-sized cartoon monkey is posed in front of the viewer.
The monkey is adorned with a brown head, a brown vest, and brown pants.
Its arms are draped over its chest, adding a touch of balance to the
scene. A yellow bottle with a yellow label, adorned with the word "MONKEY"
is positioned to the left of the monkey, positioned in a way that creates
a stark contrast to the monkeys body. The bottles cap, a yellowish-orange
color, adds a pop of color to the composition. Three bananas are arranged
to the bottom right corner of the frame.
output:
url: images/1.png
- text: >-
Claymation, a small cartoon figure stands against a stark white backdrop.
The figures face is adorned with a black t-shirt, gray shorts, black
shoes, and a pair of white socks. The head of the figure is adorned in a
light brown beanie with a white patch on it that reads "KUBO". The figure
is holding a wooden baseball bat in its left hand, with the word "OKUBO"
written on it in black.
output:
url: images/3.png
- text: >-
Claymation, a medium-sized cartoon figure stands against a stark yellow
backdrop. The figures head is adorned with a gold crown, adorned with
small gold dots, adding a pop of color to the scene. Its eyes are wide
open, revealing a glimpse of black eyebrows and black eyelashes. Its head
is encircled by a gold ribbon, adding depth to the composition. Its outfit
is adorned in a cream-colored dress with a brown belt, adding to the
overall composition.
output:
url: images/2.png
- text: >-
Claymation, a small cartoon figure stands against a stark white backdrop.
The figures face is adorned with black eyes, a black headband, and a pair
of red shorts with a white belt tied around the waist. The word "KUBO" is
written in black letters on the chest of the figure, along with the word
"UBO" in a smaller font. A life preserver is in its right hand, adding a
touch of color to the figure.
output:
url: images/4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Claymation
license: creativeml-openrail-m
Model description for Flux-Ghibli-Art-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 | 16 & 2000 |
Epoch | 10 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 17
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-Claymation-XC-LoRA"
trigger_word = "Claymation"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use Claymation
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.