Image-to-Video
fansam39 commited on
Commit
427e36f
·
verified ·
1 Parent(s): 80d7a57

Update README: link to LongE2V-data dataset and usage instructions

Browse files
Files changed (1) hide show
  1. README.md +25 -0
README.md CHANGED
@@ -1,3 +1,28 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+
5
+ # LongE2V
6
+
7
+ Released LoRA weights for **LongE2V**, fine-tuned on top of `THUDM/CogVideoX-5b-I2V`.
8
+
9
+ - **Code**: training and evaluation scripts for this model are in the LongE2V code repository.
10
+ - **Data**: preprocessed evaluation/training data (ECD, HQF, MVSEC) is released at [fansam39/LongE2V-data](https://huggingface.co/datasets/fansam39/LongE2V-data).
11
+
12
+ ## Files
13
+
14
+ - `pytorch_lora_weights.safetensors`: LoRA weights for the CogVideoX-5b-I2V base model.
15
+
16
+ ## Usage
17
+
18
+ ```bash
19
+ WEIGHT_URL=https://huggingface.co/fansam39/LongE2V/resolve/main/pytorch_lora_weights.safetensors bash scripts/download_weights.sh
20
+ ```
21
+
22
+ Or with the Hugging Face CLI:
23
+
24
+ ```bash
25
+ hf download fansam39/LongE2V pytorch_lora_weights.safetensors --local-dir weights
26
+ ```
27
+
28
+ See the code repository's README for full inference and evaluation instructions.