Release beta v0.3 model checkpoint
Browse files
README.md
CHANGED
|
@@ -61,10 +61,14 @@ Inspired by [In-Context-LoRA](https://github.com/ali-vilab/I
|
|
| 61 |
|
| 62 |
> **_NOTE:_** This is a beta release of the model. The consistency between views may not be perfect, and the model might sometimes generate views that don't perfectly align or maintain exact object positions across viewpoints. I am working on improving the geometric consistency and spatial relationships between generated views.
|
| 63 |
|
|
|
|
|
|
|
|
|
|
| 64 |
|
| 65 |
## Roadmap
|
| 66 |
|
| 67 |
-
- [
|
|
|
|
| 68 |
- [ ] 4️⃣ Generate 4 views of a scene in a grid format.
|
| 69 |
- [ ] 🧸 Generate 4 canonical coordinates view points of a single object in a grid format.
|
| 70 |
- [ ] 🏛️ 3D reconstruction from multi-view images.
|
|
|
|
| 61 |
|
| 62 |
> **_NOTE:_** This is a beta release of the model. The consistency between views may not be perfect, and the model might sometimes generate views that don't perfectly align or maintain exact object positions across viewpoints. I am working on improving the geometric consistency and spatial relationships between generated views.
|
| 63 |
|
| 64 |
+
## News
|
| 65 |
+
|
| 66 |
+
- 2024-11-25: Release beta v0.3 model checkpoint, the consistency between views has been improved a lot compared to the previous version.
|
| 67 |
|
| 68 |
## Roadmap
|
| 69 |
|
| 70 |
+
- [x] 🔄 Improve the consistency between the two-view images.
|
| 71 |
+
- [ ] Add camera control to the prompt to manage the similarity between the two views.
|
| 72 |
- [ ] 4️⃣ Generate 4 views of a scene in a grid format.
|
| 73 |
- [ ] 🧸 Generate 4 canonical coordinates view points of a single object in a grid format.
|
| 74 |
- [ ] 🏛️ 3D reconstruction from multi-view images.
|