---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: '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.'
  output:
    url: images/PP1.png
- text: 'poster foss, A poster of a womans face with the words "STRANGER THINGS" at the bottom. The womans eyes are closed and her lips are slightly parted. Her hair is dark brown and she is wearing a red, white, and blue bandana on her head. The bandana has white stars on it. The background of the poster is yellow, red, and white stripes. The words "NETFLIX" are written in black on the top left corner.'
  output:
    url: images/PP2.png
- text: 'poster foss, A comic book cover features a man with a beard and mustache. He is wearing a white collared shirt and a plaid jacket. Behind him is a man in a red and black mask. Above the man is the word "DEADPOOL AND WOLVERINE" in bold yellow letters. To the left of the man in the mask is a yellow sign with the words "SINGLE TAKEN" written on it in red letters.'
  output:
    url: images/PP3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: poster foss
license: creativeml-openrail-m
---
# Flux.1-Dev-Poster-HQ-LoRA

<Gallery />

**The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.**

## Model description 

**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

## Best Dimensions

- 768 x 1024 (Best)
- 1024 x 1024 (Default)
    
## Setting Up
```python
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)
```

## Trigger words

You should use `poster foss` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Flux.1-Dev-Poster-HQ-LoRA/tree/main) them in the Files & versions tab.