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("Nercy/flux-dalle")
prompt = "A serene Japanese zen garden with cherry blossoms, golden sunlight, and a traditional stone pathway"
image = pipe(prompt).images[0]flux dalle
- Prompt
- A serene Japanese zen garden with cherry blossoms, golden sunlight, and a traditional stone pathway
- Prompt
- A surreal dreamlike landscape with floating islands, impossible geometric shapes, and ethereal pastel color palette
- Prompt
- owl in anime style, some fantasy in the background, super realistic lighting
Model description
This model is based on black-forest-labs/FLUX.1-dev and is designed for text-to-image generation. It uses LoRA (Low-Rank Adaptation) and diffusers for efficient and high-quality image synthesis. The model is optimized for generating images from textual prompts, particularly in a style reminiscent of DALL-E.
Trigger words
Use the trigger word dalle to activate the image generation process.
Download model
Weights for this model are available in Safetensors format. You can download them from the Files & versions tab.
License
This model is licensed under the Flux-1-Dev Non-Commercial License. For more details, refer to the license.
- Downloads last month
- 30
Model tree for Nercy/flux-dalle
Base model
black-forest-labs/FLUX.1-dev