metadata
tags:
- text-to-image
- lora
- diffusers
- template:sd-lora
- ai-toolkit
base_model: Qwen/Qwen-Image
license: creativeml-openrail-m
inference:
parameters:
width: 1024
height: 1024
widget:
- text: a mad scientist laboratory interior
output:
url: images/1.png
- text: a restaurant kitchen interior
output:
url: images/3.png
- text: a small street at Mikonos, greece
output:
url: images/4.png
- text: cartoon style illustration of a tv studio
output:
url: images/5.png
- text: >-
cartoon style illustration of a tv studio. There is a big quiz show set.
There are color lights. Many cameras are pointing to the main stage.
output:
url: images/6.png
panorama-qwen-image-lora
Model trained with AI Toolkit by Ostris
It generates panoramic/fisheye/360 images.
Gallery
- Prompt
- a mad scientist laboratory interior
- Prompt
- a restaurant kitchen interior
- Prompt
- a small street at Mikonos, greece
- Prompt
- cartoon style illustration of a tv studio
- Prompt
- cartoon style illustration of a tv studio. There is a big quiz show set. There are color lights. Many cameras are pointing to the main stage.
Trigger words
No trigger words defined.
Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('Qwen/Qwen-Image', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('lichorosario/fisheye_v3-qwen-image-lora', weight_name='fisheye_v3-qwen-image_000002500.safetensors')
image = pipeline('a beautiful landscape').images[0]
image.save("my_image.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers