README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
    autumnProxy orange and red tree surrounded by grass and leaves with a double
    rainbow in the sky above the tree
  parameters:
    negative_prompt: cartoon, fake
  output:
    url: images/seasonallandsfluxdev_000100_04_20241227200714.png
- text: 'autumnProxy red and green maple tree looking up at from underneath '
  parameters:
    negative_prompt: cartoon, fake
  output:
    url: images/seasonallandsflux_001500_03_20241227091256.png
- text: >-
    autumnProxy orange and red tree surrounded by grass and leaves with a double
    rainbow in the sky above the tree
  parameters:
    negative_prompt: cartoon, fake
  output:
    url: images/seasonallandsfluxdev_000400_04_20241227222430.png
- text: autumnProxy orange and green maple leaf
  parameters:
    negative_prompt: cartoon, fake
  output:
    url: images/seasonallandsfluxdev_000900_00_20241228020648.png
- text: autumnProxy red and green leaf
  parameters:
    negative_prompt: cartoon, fake
  output:
    url: images/seasonallandsfluxdev_000400_02_20241227221919.png
- text: autumnProxy red maple leaf
  parameters:
    negative_prompt: cartoon, fake
  output:
    url: images/seasonallandsfluxdev_000200_02_20241227204642.png
- text: >-
    autumnProxy a red and yellow maple leaf resting on a wooden surface. The
    leaf is vibrant and stands out against the wooden background, its colors of
    red, yellow, and orange creating a beautiful contrast, almost marbled and
    blocky.
  output:
    url: images/example_ahrux3gu3.png
- text: >-
    autumnProxy a red and yellow maple leaf resting on a wooden surface. The
    leaf is vibrant and stands out against the wooden background, its colors of
    red, yellow, and orange creating a beautiful contrast, almost marbled and
    blocky.
  output:
    url: images/d7224216-f97d-449e-a0ce-507cefc575f4.jpg
- text: >-
    autumnProxy a wizard castle with outside castle walls covered in red and
    green ivy
  output:
    url: images/example_c9md0cjot.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: autumnProxy
license: apache-2.0

---
# FLUX.1-dev-LoRA-AutumnSpringTrees

<Gallery />

## Model description 

# FLUX.1-dev-LoRA-AutumnSpringTrees LoRA

A LoRA fine-tune for FLUX.1 [dev] that specializes in generating seasonal landscapes with a focus on autumn scenery, foliage, and natural environments. Trained using Fluxgym, by cocktail peanut: https://github.com/cocktailpeanut/fluxgym utilizing my own hand collected autumn/spring plant photos dataset.

## Overview
This LoRA enhances FLUX.1 [dev]&#39;s ability to generate detailed autumn landscapes with rich, vibrant fall colors, detailed trees, and seasonal elements. Use the trigger word &#x60;autumnProxy&#x60; to activate the autumn-specific capabilities.

## Installation

First, ensure you have FLUX.1 [dev] installed:

```python
# Install
pip install -U diffusers

# Loading with Diffusers
import torch
from diffusers import FluxPipeline

# Load base model
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

# Load and apply LoRA weights
pipe.load_lora_weights("Borcherding/FLUX.1-dev-LoRA-AutumnSpringTrees-lora")

# Generate image
prompt = "autumnProxy A majestic maple tree with vibrant red and orange leaves, golden afternoon light"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=3.5,
    num_inference_steps=50,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0]
image.save("autumn-scene.png")

# Unload LoRA weights if needed
pipe.unload_lora_weights()

# Optional: Merge LoRA weights permanently
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Borcherding/FLUX.1-dev-LoRA-AutumnSpringTrees")
pipe.merge_lora_weights()
pipe.save_pretrained("FLUX.1-dev-LoRA-AutumnSpringTrees-merged")
```

# Trigger Word

Use autumnProxy in your prompts to activate the seasonal enhancements
Best results achieved when placing the trigger word at the start of the prompt

Prompt Examples
&quot;autumnProxy A peaceful forest path covered in fallen maple leaves, morning mist rising&quot;
&quot;autumnProxy Ancient oak trees with twisted branches, leaves turning golden and red&quot;
&quot;autumnProxy Scenic mountain valley with autumn colors, warm sunset light&quot;
Specialized Features

Enhanced autumn color palette (reds, oranges, yellows, greens)
Detailed tree and leaf structures
Natural seasonal lighting effects
Atmospheric elements like fog and mist
Realistic ground coverage with fallen leaves

# Limitations

This is a LoRA for FLUX.1 [dev] and requires the base model to function
Focus on natural landscapes and seasonal elements
Inherits base limitations from FLUX.1 [dev]

License
This LoRA falls under the same licensing terms as FLUX.1 [dev]. Please refer to the base model&#39;s license for usage terms.
Credits

Base model: FLUX.1 [dev] by Black Forest Labs
LoRA training and development: [Borcherding at BorchInk]


## Trigger words

You should use `autumnProxy` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/Borcherding/FLUX.1-dev-LoRA-AutumnSpringTrees-lora/tree/main) them in the Files & versions tab.