MuteApo commited on
Commit
40ca72a
Β·
verified Β·
1 Parent(s): 4d69a59

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -19
README.md CHANGED
@@ -3,7 +3,6 @@ license: mit
3
  ---
4
  # CamI2V: Camera-Controlled Image-to-Video Diffusion Model
5
 
6
-
7
  <div align="center">
8
  <a href="https://arxiv.org/abs/2410.15957">
9
  <img src="https://img.shields.io/static/v1?label=arXiv&message=2410.15957&color=b21d1a" style="display: inline-block; vertical-align: middle;">
@@ -16,22 +15,6 @@ license: mit
16
  </a>
17
  </div>
18
 
19
-
20
- ## 🌟 News and Todo List
21
-
22
-
23
- - πŸ”₯ 25/03/17: Upload test metadata used in our paper to make easier evaluation.
24
- - πŸ”₯ 25/02/15: Release demo of [RealCam-I2V](https://zgctroy.github.io/RealCam-I2V/) for real-world applications, code will be available at [repo](https://github.com/ZGCTroy/RealCam-I2V).
25
- - πŸ”₯ 25/01/12: Release checkpoint of [CamI2V (512x320, 100k)](https://huggingface.co/MuteApo/CamI2V/blob/main/512_cami2v_100k.pt). We plan to release a more advanced model with longer training soon.
26
- - πŸ”₯ 25/01/02: Release checkpoint of [CamI2V (512x320, 50k)](https://huggingface.co/MuteApo/CamI2V/blob/main/512_cami2v_50k.pt), which is suitable for research propose and comparison.
27
- - πŸ”₯ 24/12/24: Integrate [Qwen2-VL](https://github.com/QwenLM/Qwen2-VL) in gradio demo, you can now caption your own input image by this powerful VLM.
28
- - πŸ”₯ 24/12/23: Release checkpoint of [CamI2V (256x256, 50k)](https://huggingface.co/MuteApo/CamI2V/blob/main/256_cami2v.pt).
29
- - πŸ”₯ 24/12/16: Release reproduced non-official checkpoints of [MotionCtrl (256x256, 50k)](https://huggingface.co/MuteApo/CamI2V/blob/main/256_motionctrl.pt) and [CameraCtrl (256x256, 50k)](https://huggingface.co/MuteApo/CamI2V/blob/main/256_cameractrl.pt) on [DynamiCrafter](https://github.com/Doubiiu/DynamiCrafter).
30
- - πŸ”₯ 24/12/09: Release training configs and scripts.
31
- - πŸ”₯ 24/12/06: Release [dataset pre-process code](datasets) for RealEstate10K.
32
- - πŸ”₯ 24/12/02: Release [evaluation code](evaluation) for RotErr, TransErr, CamMC and FVD.
33
- - 🌱 24/11/16: Release model code of CamI2V for training and inference, including implementation for MotionCtrl and CameraCtrl.
34
-
35
  ## πŸŽ₯ Gallery
36
 
37
  <table>
@@ -69,6 +52,20 @@ license: mit
69
  </tr>
70
  </table>
71
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
  ## πŸ“ˆ Performance
73
 
74
  Measured under 256x256 resolution, 50k training steps, 25 DDIM steps, text-image CFG 7.5, camera CFG 1.0 (no camera CFG).
@@ -141,7 +138,6 @@ python cami2v_gradio_app.py --use_qwenvl_captioner
141
 
142
  Gradio may struggle to establish network connection, please re-try with `--use_host_ip`.
143
 
144
-
145
  ## πŸ€— Related Repo
146
 
147
  [RealCam-I2V: https://github.com/ZGCTroy/RealCam-I2V](https://github.com/ZGCTroy/RealCam-I2V)
@@ -152,7 +148,6 @@ Gradio may struggle to establish network connection, please re-try with `--use_h
152
 
153
  [DynamiCrafter: https://github.com/Doubiiu/DynamiCrafter](https://github.com/Doubiiu/DynamiCrafter)
154
 
155
-
156
  ## πŸ—’οΈ Citation
157
 
158
  ```
 
3
  ---
4
  # CamI2V: Camera-Controlled Image-to-Video Diffusion Model
5
 
 
6
  <div align="center">
7
  <a href="https://arxiv.org/abs/2410.15957">
8
  <img src="https://img.shields.io/static/v1?label=arXiv&message=2410.15957&color=b21d1a" style="display: inline-block; vertical-align: middle;">
 
15
  </a>
16
  </div>
17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  ## πŸŽ₯ Gallery
19
 
20
  <table>
 
52
  </tr>
53
  </table>
54
 
55
+ ## 🌟 News and Todo List
56
+
57
+ - πŸ”₯ 25/03/17: Upload test metadata used in our paper to make easier evaluation.
58
+ - πŸ”₯ 25/02/15: Release demo of [RealCam-I2V](https://zgctroy.github.io/RealCam-I2V/) for real-world applications, code will be available at [repo](https://github.com/ZGCTroy/RealCam-I2V).
59
+ - πŸ”₯ 25/01/12: Release checkpoint of [CamI2V (512x320, 100k)](https://huggingface.co/MuteApo/CamI2V/blob/main/512_cami2v_100k.pt). We plan to release a more advanced model with longer training soon.
60
+ - πŸ”₯ 25/01/02: Release checkpoint of [CamI2V (512x320, 50k)](https://huggingface.co/MuteApo/CamI2V/blob/main/512_cami2v_50k.pt), which is suitable for research propose and comparison.
61
+ - πŸ”₯ 24/12/24: Integrate [Qwen2-VL](https://github.com/QwenLM/Qwen2-VL) in gradio demo, you can now caption your own input image by this powerful VLM.
62
+ - πŸ”₯ 24/12/23: Release checkpoint of [CamI2V (256x256, 50k)](https://huggingface.co/MuteApo/CamI2V/blob/main/256_cami2v.pt).
63
+ - πŸ”₯ 24/12/16: Release reproduced non-official checkpoints of [MotionCtrl (256x256, 50k)](https://huggingface.co/MuteApo/CamI2V/blob/main/256_motionctrl.pt) and [CameraCtrl (256x256, 50k)](https://huggingface.co/MuteApo/CamI2V/blob/main/256_cameractrl.pt) on [DynamiCrafter](https://github.com/Doubiiu/DynamiCrafter).
64
+ - πŸ”₯ 24/12/09: Release training configs and scripts.
65
+ - πŸ”₯ 24/12/06: Release [dataset pre-process code](datasets) for RealEstate10K.
66
+ - πŸ”₯ 24/12/02: Release [evaluation code](evaluation) for RotErr, TransErr, CamMC and FVD.
67
+ - 🌱 24/11/16: Release model code of CamI2V for training and inference, including implementation for MotionCtrl and CameraCtrl.
68
+
69
  ## πŸ“ˆ Performance
70
 
71
  Measured under 256x256 resolution, 50k training steps, 25 DDIM steps, text-image CFG 7.5, camera CFG 1.0 (no camera CFG).
 
138
 
139
  Gradio may struggle to establish network connection, please re-try with `--use_host_ip`.
140
 
 
141
  ## πŸ€— Related Repo
142
 
143
  [RealCam-I2V: https://github.com/ZGCTroy/RealCam-I2V](https://github.com/ZGCTroy/RealCam-I2V)
 
148
 
149
  [DynamiCrafter: https://github.com/Doubiiu/DynamiCrafter](https://github.com/Doubiiu/DynamiCrafter)
150
 
 
151
  ## πŸ—’οΈ Citation
152
 
153
  ```