README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
    Master Claymation, A mid-shot on a sandy beige backdrop, three plastic
    figures walk in unison, dressed in desert-themed outfits: beige overalls,
    linen scarves, and boots dusted with fine powder. The central figure wears
    aviator goggles and holds a mini compass. The light is warm, evoking the
    glow of a setting sun in a stop-motion desert expedition.
  output:
    url: images/1.png
- text: >-
    Master Claymation, Shot in a moody side-lit studio, two figurines are seated
    at a miniature café table, drinking from tiny mugs. The female mannequin on
    the left has curly lavender hair and wears a forest green trench coat, while
    the male on the right sports a yellow scarf and a pinstriped suit. A
    miniature potted plant sits between them, and soft jazz music seems to echo
    in the imaginary atmosphere
  output:
    url: images/2.png
- text: >-
    Master Claymation, At dusk on a dark violet backdrop, five miniature
    mannequins with weathered, cracked plastic skin stand in formation. They
    wear matching forest green trench coats, black gloves, and rounded silver
    helmets. Each mannequin is facing forward, except the last, who glances
    ominously to the left.
  output:
    url: images/3.png
- text: >-
    Master Claymation, captured from a low angle, a plastic figurine of a golden
    retriever stands proudly on a bright teal background. Its fur is sculpted
    with wavy golden textures, and it wears a red bandana with a paw print
    pattern. Its tongue sticks out playfully, and its tail is mid-wag.
  output:
    url: images/4.png
- text: >-
    Master Claymation, captured from a side profile on a soft lavender backdrop,
    a single plastic figurine of a cat sits elegantly. The cat has glossy black
    fur with subtle gray streaks, bright green eyes, and a golden bell on a red
    collar. Its tail curls around its front paws, giving off a poised, regal
    vibe.
  output:
    url: images/5.png
- text: >-
    Master Claymation, Captured at eye-level, a close-up shot captures a blue
    plastic figurine of a mans face, adorned with a blue mustache and a blue
    ribbed collar. The figurines head is adorned with blue braids, adding a
    touch of color to the scene. The backdrop is a vibrant shade of blue,
    creating a stark contrast to the figurine.
  output:
    url: images/6.png
instance_prompt: Master Claymation
license: other
---

<pre align="center">
  
 ______  ______   __       __  __   ______   ______   __  __   ______       __   ______    
/\  == \/\  __ \ /\ \     /\ \_\ \ /\  ___\ /\  == \ /\ \/\ \ /\___  \     /\ \ /\  __ \   
\ \  _-/\ \ \/\ \\ \ \____\ \____ \\ \ \____\ \  __< \ \ \_\ \\/_/  /__    \ \ \\ \ \/\ \  
 \ \_\   \ \_____\\ \_____\\/\_____\\ \_____\\ \_\ \_\\ \_____\ /\_____\    \ \_\\ \_____\ 
  \/_/    \/_____/ \/_____/ \/_____/ \/_____/ \/_/ /_/ \/_____/ \/_____/     \/_/ \/_____/ 
                                                                                                                                                                                                  
</pre>

# claymation

<Gallery />

---

# Model description for 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           | 28 & 3450 |
| Epoch                     | 27   | Save Every N Epochs       | 1    |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 45

## 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

```python
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 = "Polycruz9/claymation"
trigger_word = "Master Claymation"  
pipe.load_lora_weights(lora_repo)

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

## Trigger words

You should use `Master Claymation` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/Polycruz9/claymation/tree/main) them in the Files & versions tab.