Downloads · 30 days
0
zimage-artist-loras
Chungus817/zimage-artist-loras
zimage-artist-loras is a machine learning model from Chungus817. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Style LoRAs trained on Z-Image base model (Tongyi-MAI/Z-Image).
Access
Public
Updated Feb 1, 2026
Repo size
2.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.6 GB · 100%
At a glance
- Access
- Public
- Created
- Jan 30, 2026
- Updated
- Feb 1, 2026
- SHA
- 6f07e1af
Model card
From the Hugging Face model README
Z-Image Artist LoRAs
Style LoRAs trained on Z-Image base model (Tongyi-MAI/Z-Image).
LoRAs
| LoRA | Trigger | Style |
|---|---|---|
yoruuu_v1.safetensors | <yoruuu> | Soft, dreamy anime aesthetic |
utdt69_v1.safetensors | <utdt69> | Glitch effects, vibrant colors |
Usage
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"Tongyi-MAI/Z-Image",
torch_dtype=torch.bfloat16,
)
pipe.to("cuda")
# Load LoRA
pipe.load_lora_weights("Chungus817/zimage-artist-loras", weight_name="yoruuu_v1.safetensors")
image = pipe(
prompt="<yoruuu>, anime girl, soft lighting, detailed",
negative_prompt="lowres, bad quality, blurry",
num_inference_steps=28,
guidance_scale=4.0,
).images[0]
Training Details
- Base model: Tongyi-MAI/Z-Image (6B params)
- Training: ai-toolkit (ostris)
- Steps: 3000
- LoRA rank: 16
- Learning rate: 1e-4
- Images per artist: 50
License
Apache 2.0 (following Z-Image base model)
- Created
- Jan 30, 2026
- Updated
- Feb 1, 2026