Instructions to use Alisson990/thumbnail-lora-flux2-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Alisson990/thumbnail-lora-flux2-dev 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.2-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Alisson990/thumbnail-lora-flux2-dev") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
metadata
base_model: black-forest-labs/FLUX.2-dev
tags:
- lora
- flux
- flux2
- youtube-thumbnails
- diffusers
license: other
license_name: flux-dev-non-commercial-license
library_name: diffusers
pipeline_tag: text-to-image
YouTube Thumbnail LoRA -- FLUX.2-dev
| Parametro | Valor |
|---|---|
| Base Model | black-forest-labs/FLUX.2-dev |
| Dataset | Alisson990/snn_compute |
| Steps | 3000 |
| LoRA Rank | 32 |
| LR | 0.0001 |
| Resolucao | 1280x720 |
| Batch efetivo | 8 |