import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Jigen/qwen-image-capybara")
prompt = "photograph of a capybara standing on its hind legs, it wears a knitted sweater which is bright white, but with black lettering on it that says 'Capybara for Qwen-Image' The background is black."
image = pipe(prompt).images[0]Capybara for Qwen-Image
- Prompt
- photograph of a capybara standing on its hind legs, it wears a knitted sweater which is bright white, but with black lettering on it that says 'Capybara for Qwen-Image' The background is black.
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
Model description
Qwen Image (original model, not 2512).
See uploaded image ComfyUI prompts for example prompts.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 6
Model tree for Jigen/qwen-image-capybara
Base model
Qwen/Qwen-Image