Update README.md
Browse files
README.md
CHANGED
|
@@ -73,6 +73,8 @@ Inspired by [In-Context-LoRA](https://github.com/ali-vilab/I
|
|
| 73 |
- [ ] 🧸 Generate 4 canonical coordinates view points of a single object in a grid format.
|
| 74 |
- [ ] 🏛️ 3D reconstruction from multi-view images.
|
| 75 |
|
|
|
|
|
|
|
| 76 |
## Inference
|
| 77 |
|
| 78 |
```python
|
|
|
|
| 73 |
- [ ] 🧸 Generate 4 canonical coordinates view points of a single object in a grid format.
|
| 74 |
- [ ] 🏛️ 3D reconstruction from multi-view images.
|
| 75 |
|
| 76 |
+
When applying the LoRA to the FluxInpaint Pipeline, I noticed significant degradation in consistency between the generated and input views. Therefore, I plan to also train the LoRA for the FluxFill model instead of the original Flux text-to-image model to improve performance.
|
| 77 |
+
|
| 78 |
## Inference
|
| 79 |
|
| 80 |
```python
|