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("MultiTrickFox/Flux-LoRA-Equirectangular-v3")
prompt = "equirectangular 360 degree panorama"
image = pipe(prompt).images[0]Flux LoRA Equirectangular v3
- Prompt
- equirectangular 360 degree panorama
- Negative Prompt
- blurry
Model description
Usage
Trigger Keyword: "equirectangular 360 degree panorama"
Image resolution: always 2:1 aspect 1024 x 512 , 1408 x 704 works best. 2048 x 1024 also works.
LoRA Weight: 0.5 to 1.5
Flux Guidance: 2.5 for realistic scenes
Details
Imported from: https://civitai.com/models/735980/flux-equirectangular-360-panorama
Read the workflow: https://civitai.com/models/745010?modelVersionId=833115
360 Equirectangular Viewer: https://renderstuff.com/tools/360-panorama-web-viewer
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 64
Model tree for MultiTrickFox/Flux-LoRA-Equirectangular-v3
Base model
black-forest-labs/FLUX.1-dev