NFT Beta
Collection
beta testing experimentals • 2 items • Updated
How to use Polycruz9/nft-experimental-beta0.1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Polycruz9/nft-experimental-beta0.1")
prompt = "3D avatar NFT of a futuristic cartoon cyber monkey standing confidently on two legs, styled with chrome-finished cybernetic limbs and a half-mechanical face. The monkey wears a neon purple tech jacket with glowing circuit patterns and a thick, metallic $ dollar chain. One eye is replaced by a glowing red visor; the other is enhanced with a blue lens interface. He has sleek wireless ear pods and a holographic keyboard floating at his side. A micro-server backpack with blinking lights is strapped to his back, and his tail is wrapped in LED wiring. Set against a clean white background with soft studio lighting and light shadow beneath the feet."
image = pipe(prompt).images[0]pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Polycruz9/nft-experimental-beta0.1")
prompt = "3D avatar NFT of a futuristic cartoon cyber monkey standing confidently on two legs, styled with chrome-finished cybernetic limbs and a half-mechanical face. The monkey wears a neon purple tech jacket with glowing circuit patterns and a thick, metallic $ dollar chain. One eye is replaced by a glowing red visor; the other is enhanced with a blue lens interface. He has sleek wireless ear pods and a holographic keyboard floating at his side. A micro-server backpack with blinking lights is strapped to his back, and his tail is wrapped in LED wiring. Set against a clean white background with soft studio lighting and light shadow beneath the feet."
image = pipe(prompt).images[0]
______ ______ __ __ __ ______ ______ __ __ ______ __ ______
/\ == \/\ __ \ /\ \ /\ \_\ \ /\ ___\ /\ == \ /\ \/\ \ /\___ \ /\ \ /\ __ \
\ \ _-/\ \ \/\ \\ \ \____\ \____ \\ \ \____\ \ __< \ \ \_\ \\/_/ /__ \ \ \\ \ \/\ \
\ \_\ \ \_____\\ \_____\\/\_____\\ \_____\\ \_\ \_\\ \_____\ /\_____\ \ \_\\ \_____\
\/_/ \/_____/ \/_____/ \/_____/ \/_____/ \/_/ /_/ \/_____/ \/_____/ \/_/ \/_____/









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 & 3990 |
| Epoch | 22 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 67 [ Diffusion Generated ]
| Dimensions | Aspect Ratio | Recommendation |
|---|---|---|
| 1280 x 832 | 3:2 | Best |
| 1024 x 1024 | 1:1 | Default |
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/nft-experimental-beta0.1"
trigger_word = "3d avatar nft"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use 3d avatar nft to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
# Gated model: Login with a HF token with gated access permission hf auth login