Instructions to use fwwrsd/zimage-lora-786-74692854 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fwwrsd/zimage-lora-786-74692854 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("fwwrsd/zimage-lora-786-74692854") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Z Image LoRA β 786
A personalized LoRA trained with Z Image pipeline for generating images with a specific identity.
Quick Start
Direct Download URL
https://huggingface.co/fwwrsd/zimage-lora-786-74692854/resolve/main/lora.safetensors
ComfyUI Setup
- Download
lora.safetensorsβ place inComfyUI/models/loras/ - Use LoRA Loader node
- Set trigger word:
786
Download via Command Line
wget https://huggingface.co/fwwrsd/zimage-lora-786-74692854/resolve/main/lora.safetensors -O lora_786.safetensors
huggingface-cli download fwwrsd/zimage-lora-786-74692854 lora.safetensors
Recommended Settings
| Parameter | Value |
|---|---|
| LoRA Strength | 0.7 β 1.0 |
| CFG Scale | 3.5 |
| Steps | 20 β 30 |
Trigger word: 786 β include in your prompt to activate the LoRA.
Trained for 1 epochs (final checkpoint).
Training Details
| Parameter | Value |
|---|---|
| Training Method | diffusion-pipe + DeepSpeed |
| LoRA Rank | 16 |
| Learning Rate | 1e-4 |
| Total Epochs | unknown (best: 1) |
| Resolution | 1024px |
| Dataset Size | 59 images |
| Preset | test |
| Created | 2026-03-01 |
License
Apache 2.0 β free for personal and commercial use.
Trained with NanoBanana LoRA Bot on RunPod
- Downloads last month
- 1