Downloads · 30 days
115
1% of all-time downloads
strangerzonehf/Flux-YWL-Realism-LoRA
Flux-YWL-Realism-LoRA is a text-to-image model from strangerzonehf. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
Downloads · 30 days
115
1% of all-time downloads
All-time downloads
10.2K
Public
Repo size
626 MB
Likes
28
Public
Click a slice to open those files.
.safetensors613 MB · 98%
From the Hugging Face model README

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
strangerzonehf/Flux-YWL-Realism-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 | 26 & 3100 |
| Epoch | 23 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 22 [ Hi-Res ]
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/Flux-YWL-Realism-LoRA"
trigger_word = "ylw realism"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use ylw realism to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.