YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Z Image LoRA — Trigger: 987
Training info
| Parameter | Value |
|---|---|
| Base model | Z Image (Lumina2) |
| Trigger word | 987 |
| LoRA rank | 64 |
| Epochs | 68 total (save every 5) |
| Training images | 59 |
| Learning rate | 5e-5 |
Files
Each file is a checkpoint from a different training epoch:
- \ — Epoch 5 (early, weak identity)
- \ — Epoch 10
- \ — Epoch 15
- \ — Epoch 20
- \ — Epoch 25
- \ — Epoch 30
- \ — Epoch 35
- \ — Epoch 40
- \ — Epoch 45
- More coming as training progresses...
Tip: Try different epochs. Later epochs = stronger identity but less flexibility. Earlier = more creative but weaker likeness.
Usage
Use trigger word 987 in your prompt. Example:
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support