Flux LoRA Collections
Collection
Flux THE LoRA β’ 131 items β’ Updated β’ 33
How to use prithivMLmods/Flux.1-Dev-Poster-HQ-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("prithivMLmods/Flux.1-Dev-Poster-HQ-LoRA")
prompt = "poster foss, Captured in a light brown, cartoon-like poster, the main focal point of the image is a portrait of a man in a brown collared shirt with the word \"LOKI\" written in bold black letters on the front. The mans face is covered in dark brown hair, and he is wearing a black collar around his neck. His eyes are squinted and he has a serious expression on his face. To the left of the man, there is a red circle with the number 6 on it, and to the right of the circle, there are two smaller circular circles with the same number on it. The background of the poster is black, with the words \"TALES FROM THE TIME WARRIANCE AUTHORITY\" in white letters."
image = pipe(prompt).images[0]


The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
prithivMLmods/Flux.1-Dev-Poster-HQ-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 | 15 & 1600 |
| Epoch | 10 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 13
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/Flux.1-Dev-Poster-HQ-LoRA"
trigger_word = "poster foss"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use poster foss 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