JiahuiSheng commited on
Commit
d2606d1
·
verified ·
1 Parent(s): 86f150f

Add shared backbone config and include it in checkpoint downloads

Browse files
Files changed (2) hide show
  1. README.md +8 -2
  2. config.json +12 -0
README.md CHANGED
@@ -24,10 +24,16 @@ FlashDelight suppresses the original lighting in a portrait video. FlashRelight
24
  From the FlashRelight code repository, download both checkpoints to the `weights` directory.
25
 
26
  ```bash
27
- hf download JiahuiSheng/FlashRelight flashdelight_rank0_full.pt flashrelight_rank0_full.pt --local-dir weights
28
  ```
29
 
30
- For standalone delighting, download only `flashdelight_rank0_full.pt`. Both modes also use the shared Wan2.1 configuration, VAE, text encoder, and tokenizer. [Wan2.1 base files](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B)
 
 
 
 
 
 
31
 
32
  <details>
33
  <summary>SHA-256 checksums</summary>
 
24
  From the FlashRelight code repository, download both checkpoints to the `weights` directory.
25
 
26
  ```bash
27
+ hf download JiahuiSheng/FlashRelight config.json flashdelight_rank0_full.pt flashrelight_rank0_full.pt --local-dir weights
28
  ```
29
 
30
+ For standalone delighting, download the configuration and first-stage checkpoint.
31
+
32
+ ```bash
33
+ hf download JiahuiSheng/FlashRelight config.json flashdelight_rank0_full.pt --local-dir weights
34
+ ```
35
+
36
+ Both stages use the shared backbone settings in `config.json`. The inference code applies the stage-specific input dimensions and LoRA settings. Both modes also require the Wan2.1 VAE, text encoder, and tokenizer. [Wan2.1 base files](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B)
37
 
38
  <details>
39
  <summary>SHA-256 checksums</summary>
config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dim": 1536,
3
+ "eps": 1e-06,
4
+ "ffn_dim": 8960,
5
+ "freq_dim": 256,
6
+ "in_dim": 16,
7
+ "model_type": "t2v",
8
+ "num_heads": 12,
9
+ "num_layers": 30,
10
+ "out_dim": 16,
11
+ "text_len": 512
12
+ }