AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity

refactor out reearrange

Browse Source
This commit is contained in:
yiyixuxu
2025-07-28 20:07:31 +02:00
parent 5709f7e04d
commit 0ab2e4fd91
5 changed files with 221 additions and 178 deletions
Download Patch File Download Diff File Expand all files Collapse all files

217
scripts/convert_wan_to_diffusers.py
View File

@@ -344,7 +344,7 @@ def get_transformer_config(model_type: str) -> Tuple[Dict[str, Any], ...]:
return config, RENAME_DICT, SPECIAL_KEYS_REMAP
def convert_transformer(model_type: str, stage: str=None):
def convert_transformer(model_type: str, stage: str = None):
config, RENAME_DICT, SPECIAL_KEYS_REMAP = get_transformer_config(model_type)
diffusers_config = config["diffusers_config"]
@@ -580,115 +580,116 @@ def convert_vae():
vae.load_state_dict(new_state_dict, strict=True, assign=True)
return vae
vae22_diffusers_config = {
"base_dim": 160,
"z_dim": 48,
"is_residual": True,
"in_channels": 12,
"out_channels": 12,
"decoder_base_dim": 256,
"scale_factor_temporal": 4,
"scale_factor_spatial": 16,
"patch_size": 2,
"latents_mean":[
-0.2289,
-0.0052,
-0.1323,
-0.2339,
-0.2799,
0.0174,
0.1838,
0.1557,
-0.1382,
0.0542,
0.2813,
0.0891,
0.1570,
-0.0098,
0.0375,
-0.1825,
-0.2246,
-0.1207,
-0.0698,
0.5109,
0.2665,
-0.2108,
-0.2158,
0.2502,
-0.2055,
-0.0322,
0.1109,
0.1567,
-0.0729,
0.0899,
-0.2799,
-0.1230,
-0.0313,
-0.1649,
0.0117,
0.0723,
-0.2839,
-0.2083,
-0.0520,
0.3748,
0.0152,
0.1957,
0.1433,
-0.2944,
0.3573,
-0.0548,
-0.1681,
-0.0667,
"base_dim": 160,
"z_dim": 48,
"is_residual": True,
"in_channels": 12,
"out_channels": 12,
"decoder_base_dim": 256,
"scale_factor_temporal": 4,
"scale_factor_spatial": 16,
"patch_size": 2,
"latents_mean": [
-0.2289,
-0.0052,
-0.1323,
-0.2339,
-0.2799,
0.0174,
0.1838,
0.1557,
-0.1382,
0.0542,
0.2813,
0.0891,
0.1570,
-0.0098,
0.0375,
-0.1825,
-0.2246,
-0.1207,
-0.0698,
0.5109,
0.2665,
-0.2108,
-0.2158,
0.2502,
-0.2055,
-0.0322,
0.1109,
0.1567,
-0.0729,
0.0899,
-0.2799,
-0.1230,
-0.0313,
-0.1649,
0.0117,
0.0723,
-0.2839,
-0.2083,
-0.0520,
0.3748,
0.0152,
0.1957,
0.1433,
-0.2944,
0.3573,
-0.0548,
-0.1681,
-0.0667,
],
"latents_std": [
0.4765,
1.0364,
0.4514,
1.1677,
0.5313,
0.4990,
0.4818,
0.5013,
0.8158,
1.0344,
0.5894,
1.0901,
0.6885,
0.6165,
0.8454,
0.4978,
0.5759,
0.3523,
0.7135,
0.6804,
0.5833,
1.4146,
0.8986,
0.5659,
0.7069,
0.5338,
0.4889,
0.4917,
0.4069,
0.4999,
0.6866,
0.4093,
0.5709,
0.6065,
0.6415,
0.4944,
0.5726,
1.2042,
0.5458,
1.6887,
0.3971,
1.0600,
0.3943,
0.5537,
0.5444,
0.4089,
0.7468,
0.7744,
"latents_std": [
0.4765,
1.0364,
0.4514,
1.1677,
0.5313,
0.4990,
0.4818,
0.5013,
0.8158,
1.0344,
0.5894,
1.0901,
0.6885,
0.6165,
0.8454,
0.4978,
0.5759,
0.3523,
0.7135,
0.6804,
0.5833,
1.4146,
0.8986,
0.5659,
0.7069,
0.5338,
0.4889,
0.4917,
0.4069,
0.4999,
0.6866,
0.4093,
0.5709,
0.6065,
0.6415,
0.4944,
0.5726,
1.2042,
0.5458,
1.6887,
0.3971,
1.0600,
0.3943,
0.5537,
0.5444,
0.4089,
0.7468,
0.7744,
],
"clip_output": False,
}