Add README with API documentation
Browse files
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# AI Trainer - RunPod Serverless
|
| 2 |
+
|
| 3 |
+
Multi-model LoRA training service using [ai-toolkit](https://github.com/ostris/ai-toolkit).
|
| 4 |
+
|
| 5 |
+
## Supported Models
|
| 6 |
+
|
| 7 |
+
| Model Key | Description | Base Model |
|
| 8 |
+
|-----------|-------------|------------|
|
| 9 |
+
| wan21_1b | Wan2.1 1.3B Video | Wan-AI/Wan2.1-T2V-1.3B-Diffusers |
|
| 10 |
+
| wan21_14b | Wan2.1 14B Video | Wan-AI/Wan2.1-T2V-14B-Diffusers |
|
| 11 |
+
| wan22_14b | Wan2.2 14B Video | ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16 |
|
| 12 |
+
| qwen_image | Qwen Image Gen | Qwen/Qwen-Image |
|
| 13 |
+
| qwen_image_edit | Qwen Image Edit | Qwen/Qwen-Image-Edit |
|
| 14 |
+
| flux_dev | FLUX.1 Dev | black-forest-labs/FLUX.1-dev |
|
| 15 |
+
| flux_schnell | FLUX.1 Schnell | black-forest-labs/FLUX.1-schnell |
|
| 16 |
+
|
| 17 |
+
## API Usage
|
| 18 |
+
|
| 19 |
+
### List Models
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
### Check Status
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
### Train LoRA
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
## RunPod Deployment
|
| 29 |
+
|
| 30 |
+
### Environment Variables
|
| 31 |
+
- HF_TOKEN: HuggingFace token for gated models
|
| 32 |
+
|
| 33 |
+
### Model Caching
|
| 34 |
+
For faster cold starts, set one of these HuggingFace repos in the RunPod "Model" field:
|
| 35 |
+
- FLUX: black-forest-labs/FLUX.1-dev
|
| 36 |
+
- Wan 2.2: ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16
|
| 37 |
+
- Qwen: Qwen/Qwen-Image
|
| 38 |
+
|
| 39 |
+
Note: RunPod only supports ONE cached model per endpoint.
|