Add model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: hp-l33/aim-xlarge
|
| 4 |
+
tags:
|
| 5 |
+
- mamba
|
| 6 |
+
- lora
|
| 7 |
+
- image-generation
|
| 8 |
+
- simpsons
|
| 9 |
+
pipeline_tag: unconditional-image-generation
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# NicolasNoya/SimpsonsMamba
|
| 13 |
+
|
| 14 |
+
LoRA fine-tuned Mamba/AiM-based cartoon image generation model.
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
- Base model: hp-l33/aim-xlarge
|
| 19 |
+
- Fine-tuning method: LoRA
|
| 20 |
+
- Dataset: Simpsons cartoons
|
| 21 |
+
- Checkpoint step: 50500
|
| 22 |
+
|
| 23 |
+
## Intended Use
|
| 24 |
+
|
| 25 |
+
This model is intended for research and educational image generation experiments.
|
| 26 |
+
|
| 27 |
+
## Example Usage
|
| 28 |
+
|
| 29 |
+
Use the local generation script in this project with the corresponding checkpoint weights.
|
| 30 |
+
|
| 31 |
+
## Training Notes
|
| 32 |
+
|
| 33 |
+
- Trained with periodic checkpointing and evaluation.
|
| 34 |
+
- This card was auto-generated and should be updated with detailed metrics and limitations.
|
| 35 |
+
|
| 36 |
+
## Limitations
|
| 37 |
+
|
| 38 |
+
Outputs may reflect biases or artifacts in the training data.
|