Prompt

Real Claymation, Captured at eye-level on a low-angle perspective, a blue figurine with a red hat on its head and a red scarf around its neck. The figurines head is positioned in the center of the frame, with two large white eyes and a black nose on its face. Its mouth is slightly open, revealing a black smile. The background is a stark white, adding a pop of color to the scene.

Prompt

Real Claymation, a green toy frog is standing on a light brown wooden table. The frogs mouth is open, revealing a red heart in its mouth. Its mouth is adorned with red beads, adding a pop of color to the scene. Above the frogs head, a white keyboard can be seen.

Prompt

Real Claymation, Captured at eye-level on a low-angle shot, two green plush toys are perched on a piece of wood. The toy on the left is facing the viewer, while the one on the right is facing away from the viewer. Both toys are made of clay, a vibrant green color, and have white teeth and a red button in the mouth. The backdrop is a lush green field, with a body of water in the distance. The sky is filled with white, fluffy clouds, adding a touch of contrast to the scene.

Prompt

Real Claymation, Captured at eye-level on a low-angle, close-up shot of a green frog and a black and white penguin. The frog and penguin are facing each other, their arms wrapped around each other. The penguins head is encircled by a red hot dog, its tongue sticking out, adding a pop of color to the scene. The background is a stark white, allowing the frog to be the focal point of the image.

Prompt

Real Claymation, Captured at eye-level on a low-angle, close-up shot of a yellow smiley face with open hands. The smiley face has two large black eyes and a wide, friendly grin. Its hands are extended forward as if offering a warm hug. The background is a stark white, making the bright yellow and expressive features stand out, adding a pop of color to the scene.

Model description for Real-Claymation

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	25 & 3100
Epoch	21	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 28

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/Real-Claymation"
trigger_word = "333 Pro Sketch"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Trigger words

You should use Real Claymation to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.