import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Ttio2/Z-Image-Turbo-pencil-sketch")
prompt = "A color pencil sketch of a gaming desktop"
image = pipe(prompt).images[0]ZImage-pencil-sketch
- Prompt
- A color pencil sketch of a gaming desktop
- Prompt
- A color pencil sketch of Apple Logo
- Prompt
- A color pencil sketch of a woman wearing yellow dress and red hat
- Prompt
- pencil sketch of a men playing basketball
- Prompt
- A color pencil sketch of red panda
- Prompt
- a pencil sketch of Lionel Messi
- Prompt
- a pencil sketch of the white house
Model description
This model is a LoRA trained on pencil sketch arts for Z-Image Turbo.
No trigger words are needed when using in ComfyUI.
Detailed guide on how to train it locally (can use a 12GB VRAM GPU such as RTX 3060)
For how to use it in ComfyUI, check out the Youtube video
Download model
Download them in the Files & versions tab.
- Downloads last month
- 99
Model tree for Ttio2/Z-Image-Turbo-pencil-sketch
Base model
Tongyi-MAI/Z-Image-Turbo