Buckets:
| # MOSS-Image LoRA Training Hub (`moss/`) | |
| Training notes and templates for character LoRAs on **MOSS-Image Base** (OpenMOSS, 5B), trained | |
| with [maltrainer](https://github.com/malcolmamal/maltrainer) on ComfyUI's single-file checkpoints. | |
| --- | |
| ## 🧭 Directory Map | |
| | Path | Description | | |
| | :--- | :--- | | |
| | 📘 **[Combined Optimizer Training Guide](docs/MOSS_IMAGE_COMBINED_OPTIMIZER_TRAINING_GUIDE.md)** | The method: train the dataset with AdamW 8-bit, Automagic3 and Prodigy at shorter-than-usual lengths, merge the three LoRAs at 0.7 each, and resize the merge to rank 8. Why it works, how to run it, and what's still open. | | |
| | 📗 **[MOSS-Image Training Guide](docs/moss-image-lora-training.md)** | maltrainer's guide to MOSS-Image LoRA training: model files, how it matches ComfyUI, the timestep distribution, the templates and the first real run. | | |
| | 🔬 **[Stacking Findings](docs/moss-image-lora-stacking-findings.md)** | The finding that started the combined method: two under-strength LoRAs, stacked at 1.0 each, gave the best results so far. | | |
| | 🛠️ **[`templates/`](templates/)** | The three member templates: [`adamw8bit`](templates/moss_image_template-adamw8bit.yaml) (60 epochs), [`automagic3`](templates/moss_image_template-automagic3.yaml) (20 epochs), [`prodigy`](templates/moss_image_template-prodigy.yaml) (30 epochs). | | |
| --- | |
| ## ⚡ The Method in Four Lines | |
| 1. **Train three times**, once per optimizer, each run kept short. | |
| 2. **Merge** the three LoRAs exactly, at strength 0.7 each (`merge_loras.py`). | |
| 3. **Resize** the rank-48 merge to rank 8 (`resize_lora.py`). | |
| 4. **Load** the result at strength 1.0. | |
| It grew out of a finding on MOSS-Image: two separately trained, under-strength LoRAs stacked at | |
| 1.0 each looked better than either one turned up. The subject adds up across runs, while each | |
| run's own errors partly cancel. | |
| ## 📦 Model Files (`Comfy-Org/MOSS-Image`) | |
| | Role | File | | |
| | :--- | :--- | | |
| | DiT (train on the **Base** model) | `diffusion_models/moss_image_base_bf16.safetensors` | | |
| | VAE | `vae/flux2_vae.safetensors` | | |
| | Text encoder (caching only) | `text_encoders/qwen3.5_9b_int8_convrot.safetensors` | | |
Xet Storage Details
- Size:
- 2.15 kB
- Xet hash:
- 88463c8d3581236a06b752a0f62141a925e5b86c062054fdb705c2a61fb83a37
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.