Add shared backbone config and include it in checkpoint downloads
Browse files- README.md +8 -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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|