Instructions to use Avener/fractal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Avener/fractal 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("Avener/fractal") prompt = "fx, moyou, Masterpiece, best quality, high resolution, (dark blue theme), (universe), (planets:1.2), (nebulae), free form surfaces, concise lines, depth of field," image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
fx, moyou, Masterpiece, best quality, high resolution, (dark blue theme),
(universe), (planets:1.2), (nebulae), free form surfaces, concise lines,
depth of field,
parameters:
negative_prompt: ' 16-token-negative-deliberate, easynegative, worst quality, low quality, grayscale, monochrome,nsfw'
output:
url: images/8a8d4213-ee1a-490b-a05d-f65691e859e1.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: null
fractal

- Prompt
- fx, moyou, Masterpiece, best quality, high resolution, (dark blue theme), (universe), (planets:1.2), (nebulae), free form surfaces, concise lines, depth of field,
- Negative Prompt
- 16-token-negative-deliberate, easynegative, worst quality, low quality, grayscale, monochrome,nsfw
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.