Flux LoRA Collections
Collection
LoRA Flux
•
51 items
•
Updated
•
14
prithivMLmods/Ton618-Amxtoon-Flux-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 | 20 & 1.8K |
Epoch | 15 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 15 [ Hi-RES ]
🧨Follwing the prompt structure is important to obtain the better results
Prompt |
---|
Amxtoon, a man with brown hair and blue eyes is standing next to a anime doll with long black hair. The doll on the left is wearing a gray t-shirt with an orange and yellow sweater draped over it. The woman on the right is smiling and looking at the camera. In the background, a painting of a fire is visible on the wall. |
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 = "prithivMLmods/Ton618-Amxtoon-Flux-LoRA"
trigger_word = "Amxtoon"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
https://x.com/DarbyBaileyXO/status/1851388809067577805
https://x.com/MaxPanRa/status/1851385552844587200
https://x.com/aimikummd/status/1851180111648669877
Data Source Obtained / Generated from playground.com
Playground: https://playground.com/
You should use Amxtoon
to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Base model
black-forest-labs/FLUX.1-dev