---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'nft avatar 3d, Captured at eye-level, a 3D rendering of a chimpanzees face, adorned with a gold jacket and a gold necklace. The chimpanzee is adorned with three gold rings, a white t-shirt, and a pair of gold sunglasses with the letters "N" on them. Its face is covered in a light yellow cap, and its ears are perked up. Its mouth is slightly open, as if it is about to take a bite out of the sunglasses. The background is a cityscape with neon lights, and cars are parked on the street. To the right of the chimpanzee, there is a yellow sign that reads "NOHET".
'
  output:
    url: images/cyber-simian-nft-streetwear-monkey_1037797-1241.png
base_model: stabilityai/stable-diffusion-3.5-large-turbo
instance_prompt: nft avatar 3d
license: apache-2.0
---

![3.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/HbXqEV0LW435Ocey5IPKk.png)

# NFT_Character_Avatar

<Gallery />

## Model description 

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           | 27 & 3800 |
| Epoch                     | 25     | Save Every N Epochs       | 1      |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 63 [Diffusion Generated]

## Setting Up

```python
from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/stable-diffusion-3.5-large-turbo"

torch_dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)

pipe.load_lora_weights("strangerzonehf/NFT_Character_Avatar-SD3.5-TURBO-Large", weight_name="nft-avatar-3d-sd35.safetensors")
trigger_word = "nft avatar 3d"  # Specify trigger word for LoRA
pipe.fuse_lora(lora_scale=1.0))
```

## Trigger words

You should use `nft avatar 3d` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/NFT_Character_Avatar-SD3.5-TURBO-Large/tree/main) them in the Files & versions tab.