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("Raelina/Flux-Pastel-Anime")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Flux Pastel Anime
You can drag and drop each image in your ComfyUI to get the workflow.
This repository provides a checkpoint with trained Lora "Pastel Anime" for FLUX.1-dev model by Black Forest Labs
Recommended Parameter Generation
- Guidance : 4
- Steps : 20-30
Training Details
- Trained with 300 images
- All images captioned with Joy-Caption
- Steps 1600
License
lora model safetensors falls under the FLUX.1 [dev] Non-Commercial License
- Downloads last month
- 100
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Raelina/Flux-Pastel-Anime
Base model
black-forest-labs/FLUX.1-dev