Instructions to use Erland/tiny-wan2.2-t2v-a14b-debug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Erland/tiny-wan2.2-t2v-a14b-debug with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Erland/tiny-wan2.2-t2v-a14b-debug", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add tiny Wan debug pipeline
Browse files- .gitattributes +1 -0
- README.md +34 -0
- model_index.json +30 -0
- scheduler/scheduler_config.json +18 -0
- text_encoder/config.json +31 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/tokenizer.json +3 -0
- tokenizer/tokenizer_config.json +317 -0
- transformer/config.json +24 -0
- transformer/diffusion_pytorch_model.safetensors +3 -0
- transformer_2/config.json +24 -0
- transformer_2/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +39 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
pipeline_tag: text-to-video
|
| 5 |
+
tags:
|
| 6 |
+
- diffusers
|
| 7 |
+
- wan
|
| 8 |
+
- tiny-random
|
| 9 |
+
- debug
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Tiny Wan2.2 T2V A14B Debug Pipeline
|
| 13 |
+
|
| 14 |
+
This is a randomly initialized, tiny Diffusers `WanPipeline` fixture for `Wan-AI/Wan2.2-T2V-A14B`.
|
| 15 |
+
Wan2.2 T2V-A14B high/low-noise expert layout represented as a Diffusers WanPipeline with `transformer` and `transformer_2`.
|
| 16 |
+
|
| 17 |
+
It is intended for fast load-path and inference-control debugging only. It is not trained and should
|
| 18 |
+
not be used for generation quality evaluation.
|
| 19 |
+
|
| 20 |
+
```python
|
| 21 |
+
from diffusers import WanPipeline
|
| 22 |
+
|
| 23 |
+
pipe = WanPipeline.from_pretrained("Erland/tiny-wan2.2-t2v-a14b-debug")
|
| 24 |
+
pipe.set_progress_bar_config(disable=True)
|
| 25 |
+
frames = pipe(
|
| 26 |
+
prompt="debug prompt",
|
| 27 |
+
height=64,
|
| 28 |
+
width=64,
|
| 29 |
+
num_frames=5,
|
| 30 |
+
num_inference_steps=1,
|
| 31 |
+
guidance_scale=1.0,
|
| 32 |
+
max_sequence_length=8,
|
| 33 |
+
).frames[0]
|
| 34 |
+
```
|
model_index.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "WanPipeline",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"boundary_ratio": 0.875,
|
| 5 |
+
"expand_timesteps": false,
|
| 6 |
+
"scheduler": [
|
| 7 |
+
"diffusers",
|
| 8 |
+
"FlowMatchEulerDiscreteScheduler"
|
| 9 |
+
],
|
| 10 |
+
"text_encoder": [
|
| 11 |
+
"transformers",
|
| 12 |
+
"UMT5EncoderModel"
|
| 13 |
+
],
|
| 14 |
+
"tokenizer": [
|
| 15 |
+
"transformers",
|
| 16 |
+
"T5Tokenizer"
|
| 17 |
+
],
|
| 18 |
+
"transformer": [
|
| 19 |
+
"diffusers",
|
| 20 |
+
"WanTransformer3DModel"
|
| 21 |
+
],
|
| 22 |
+
"transformer_2": [
|
| 23 |
+
"diffusers",
|
| 24 |
+
"WanTransformer3DModel"
|
| 25 |
+
],
|
| 26 |
+
"vae": [
|
| 27 |
+
"diffusers",
|
| 28 |
+
"AutoencoderKLWan"
|
| 29 |
+
]
|
| 30 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"base_image_seq_len": 256,
|
| 5 |
+
"base_shift": 0.5,
|
| 6 |
+
"invert_sigmas": false,
|
| 7 |
+
"max_image_seq_len": 4096,
|
| 8 |
+
"max_shift": 1.15,
|
| 9 |
+
"num_train_timesteps": 10,
|
| 10 |
+
"shift": 3.0,
|
| 11 |
+
"shift_terminal": null,
|
| 12 |
+
"stochastic_sampling": false,
|
| 13 |
+
"time_shift_type": "exponential",
|
| 14 |
+
"use_beta_sigmas": false,
|
| 15 |
+
"use_dynamic_shifting": false,
|
| 16 |
+
"use_exponential_sigmas": false,
|
| 17 |
+
"use_karras_sigmas": false
|
| 18 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"UMT5EncoderModel"
|
| 4 |
+
],
|
| 5 |
+
"classifier_dropout": 0.0,
|
| 6 |
+
"d_ff": 64,
|
| 7 |
+
"d_kv": 16,
|
| 8 |
+
"d_model": 32,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.0,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "umt5",
|
| 21 |
+
"num_decoder_layers": 1,
|
| 22 |
+
"num_heads": 2,
|
| 23 |
+
"num_layers": 1,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"transformers_version": "5.8.0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 256300
|
| 31 |
+
}
|
text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a67057c5ad727b1c51b5109e15a107e1274b4b5508fb70144558255c7754761
|
| 3 |
+
size 32849328
|
tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e87c960c36d5fbf4e7e76c2469b7eab877be7f8c5992efbf97e44d3123cc6521
|
| 3 |
+
size 16837418
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"extra_ids": 300,
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<extra_id_0>",
|
| 9 |
+
"<extra_id_1>",
|
| 10 |
+
"<extra_id_2>",
|
| 11 |
+
"<extra_id_3>",
|
| 12 |
+
"<extra_id_4>",
|
| 13 |
+
"<extra_id_5>",
|
| 14 |
+
"<extra_id_6>",
|
| 15 |
+
"<extra_id_7>",
|
| 16 |
+
"<extra_id_8>",
|
| 17 |
+
"<extra_id_9>",
|
| 18 |
+
"<extra_id_10>",
|
| 19 |
+
"<extra_id_11>",
|
| 20 |
+
"<extra_id_12>",
|
| 21 |
+
"<extra_id_13>",
|
| 22 |
+
"<extra_id_14>",
|
| 23 |
+
"<extra_id_15>",
|
| 24 |
+
"<extra_id_16>",
|
| 25 |
+
"<extra_id_17>",
|
| 26 |
+
"<extra_id_18>",
|
| 27 |
+
"<extra_id_19>",
|
| 28 |
+
"<extra_id_20>",
|
| 29 |
+
"<extra_id_21>",
|
| 30 |
+
"<extra_id_22>",
|
| 31 |
+
"<extra_id_23>",
|
| 32 |
+
"<extra_id_24>",
|
| 33 |
+
"<extra_id_25>",
|
| 34 |
+
"<extra_id_26>",
|
| 35 |
+
"<extra_id_27>",
|
| 36 |
+
"<extra_id_28>",
|
| 37 |
+
"<extra_id_29>",
|
| 38 |
+
"<extra_id_30>",
|
| 39 |
+
"<extra_id_31>",
|
| 40 |
+
"<extra_id_32>",
|
| 41 |
+
"<extra_id_33>",
|
| 42 |
+
"<extra_id_34>",
|
| 43 |
+
"<extra_id_35>",
|
| 44 |
+
"<extra_id_36>",
|
| 45 |
+
"<extra_id_37>",
|
| 46 |
+
"<extra_id_38>",
|
| 47 |
+
"<extra_id_39>",
|
| 48 |
+
"<extra_id_40>",
|
| 49 |
+
"<extra_id_41>",
|
| 50 |
+
"<extra_id_42>",
|
| 51 |
+
"<extra_id_43>",
|
| 52 |
+
"<extra_id_44>",
|
| 53 |
+
"<extra_id_45>",
|
| 54 |
+
"<extra_id_46>",
|
| 55 |
+
"<extra_id_47>",
|
| 56 |
+
"<extra_id_48>",
|
| 57 |
+
"<extra_id_49>",
|
| 58 |
+
"<extra_id_50>",
|
| 59 |
+
"<extra_id_51>",
|
| 60 |
+
"<extra_id_52>",
|
| 61 |
+
"<extra_id_53>",
|
| 62 |
+
"<extra_id_54>",
|
| 63 |
+
"<extra_id_55>",
|
| 64 |
+
"<extra_id_56>",
|
| 65 |
+
"<extra_id_57>",
|
| 66 |
+
"<extra_id_58>",
|
| 67 |
+
"<extra_id_59>",
|
| 68 |
+
"<extra_id_60>",
|
| 69 |
+
"<extra_id_61>",
|
| 70 |
+
"<extra_id_62>",
|
| 71 |
+
"<extra_id_63>",
|
| 72 |
+
"<extra_id_64>",
|
| 73 |
+
"<extra_id_65>",
|
| 74 |
+
"<extra_id_66>",
|
| 75 |
+
"<extra_id_67>",
|
| 76 |
+
"<extra_id_68>",
|
| 77 |
+
"<extra_id_69>",
|
| 78 |
+
"<extra_id_70>",
|
| 79 |
+
"<extra_id_71>",
|
| 80 |
+
"<extra_id_72>",
|
| 81 |
+
"<extra_id_73>",
|
| 82 |
+
"<extra_id_74>",
|
| 83 |
+
"<extra_id_75>",
|
| 84 |
+
"<extra_id_76>",
|
| 85 |
+
"<extra_id_77>",
|
| 86 |
+
"<extra_id_78>",
|
| 87 |
+
"<extra_id_79>",
|
| 88 |
+
"<extra_id_80>",
|
| 89 |
+
"<extra_id_81>",
|
| 90 |
+
"<extra_id_82>",
|
| 91 |
+
"<extra_id_83>",
|
| 92 |
+
"<extra_id_84>",
|
| 93 |
+
"<extra_id_85>",
|
| 94 |
+
"<extra_id_86>",
|
| 95 |
+
"<extra_id_87>",
|
| 96 |
+
"<extra_id_88>",
|
| 97 |
+
"<extra_id_89>",
|
| 98 |
+
"<extra_id_90>",
|
| 99 |
+
"<extra_id_91>",
|
| 100 |
+
"<extra_id_92>",
|
| 101 |
+
"<extra_id_93>",
|
| 102 |
+
"<extra_id_94>",
|
| 103 |
+
"<extra_id_95>",
|
| 104 |
+
"<extra_id_96>",
|
| 105 |
+
"<extra_id_97>",
|
| 106 |
+
"<extra_id_98>",
|
| 107 |
+
"<extra_id_99>",
|
| 108 |
+
"<extra_id_100>",
|
| 109 |
+
"<extra_id_101>",
|
| 110 |
+
"<extra_id_102>",
|
| 111 |
+
"<extra_id_103>",
|
| 112 |
+
"<extra_id_104>",
|
| 113 |
+
"<extra_id_105>",
|
| 114 |
+
"<extra_id_106>",
|
| 115 |
+
"<extra_id_107>",
|
| 116 |
+
"<extra_id_108>",
|
| 117 |
+
"<extra_id_109>",
|
| 118 |
+
"<extra_id_110>",
|
| 119 |
+
"<extra_id_111>",
|
| 120 |
+
"<extra_id_112>",
|
| 121 |
+
"<extra_id_113>",
|
| 122 |
+
"<extra_id_114>",
|
| 123 |
+
"<extra_id_115>",
|
| 124 |
+
"<extra_id_116>",
|
| 125 |
+
"<extra_id_117>",
|
| 126 |
+
"<extra_id_118>",
|
| 127 |
+
"<extra_id_119>",
|
| 128 |
+
"<extra_id_120>",
|
| 129 |
+
"<extra_id_121>",
|
| 130 |
+
"<extra_id_122>",
|
| 131 |
+
"<extra_id_123>",
|
| 132 |
+
"<extra_id_124>",
|
| 133 |
+
"<extra_id_125>",
|
| 134 |
+
"<extra_id_126>",
|
| 135 |
+
"<extra_id_127>",
|
| 136 |
+
"<extra_id_128>",
|
| 137 |
+
"<extra_id_129>",
|
| 138 |
+
"<extra_id_130>",
|
| 139 |
+
"<extra_id_131>",
|
| 140 |
+
"<extra_id_132>",
|
| 141 |
+
"<extra_id_133>",
|
| 142 |
+
"<extra_id_134>",
|
| 143 |
+
"<extra_id_135>",
|
| 144 |
+
"<extra_id_136>",
|
| 145 |
+
"<extra_id_137>",
|
| 146 |
+
"<extra_id_138>",
|
| 147 |
+
"<extra_id_139>",
|
| 148 |
+
"<extra_id_140>",
|
| 149 |
+
"<extra_id_141>",
|
| 150 |
+
"<extra_id_142>",
|
| 151 |
+
"<extra_id_143>",
|
| 152 |
+
"<extra_id_144>",
|
| 153 |
+
"<extra_id_145>",
|
| 154 |
+
"<extra_id_146>",
|
| 155 |
+
"<extra_id_147>",
|
| 156 |
+
"<extra_id_148>",
|
| 157 |
+
"<extra_id_149>",
|
| 158 |
+
"<extra_id_150>",
|
| 159 |
+
"<extra_id_151>",
|
| 160 |
+
"<extra_id_152>",
|
| 161 |
+
"<extra_id_153>",
|
| 162 |
+
"<extra_id_154>",
|
| 163 |
+
"<extra_id_155>",
|
| 164 |
+
"<extra_id_156>",
|
| 165 |
+
"<extra_id_157>",
|
| 166 |
+
"<extra_id_158>",
|
| 167 |
+
"<extra_id_159>",
|
| 168 |
+
"<extra_id_160>",
|
| 169 |
+
"<extra_id_161>",
|
| 170 |
+
"<extra_id_162>",
|
| 171 |
+
"<extra_id_163>",
|
| 172 |
+
"<extra_id_164>",
|
| 173 |
+
"<extra_id_165>",
|
| 174 |
+
"<extra_id_166>",
|
| 175 |
+
"<extra_id_167>",
|
| 176 |
+
"<extra_id_168>",
|
| 177 |
+
"<extra_id_169>",
|
| 178 |
+
"<extra_id_170>",
|
| 179 |
+
"<extra_id_171>",
|
| 180 |
+
"<extra_id_172>",
|
| 181 |
+
"<extra_id_173>",
|
| 182 |
+
"<extra_id_174>",
|
| 183 |
+
"<extra_id_175>",
|
| 184 |
+
"<extra_id_176>",
|
| 185 |
+
"<extra_id_177>",
|
| 186 |
+
"<extra_id_178>",
|
| 187 |
+
"<extra_id_179>",
|
| 188 |
+
"<extra_id_180>",
|
| 189 |
+
"<extra_id_181>",
|
| 190 |
+
"<extra_id_182>",
|
| 191 |
+
"<extra_id_183>",
|
| 192 |
+
"<extra_id_184>",
|
| 193 |
+
"<extra_id_185>",
|
| 194 |
+
"<extra_id_186>",
|
| 195 |
+
"<extra_id_187>",
|
| 196 |
+
"<extra_id_188>",
|
| 197 |
+
"<extra_id_189>",
|
| 198 |
+
"<extra_id_190>",
|
| 199 |
+
"<extra_id_191>",
|
| 200 |
+
"<extra_id_192>",
|
| 201 |
+
"<extra_id_193>",
|
| 202 |
+
"<extra_id_194>",
|
| 203 |
+
"<extra_id_195>",
|
| 204 |
+
"<extra_id_196>",
|
| 205 |
+
"<extra_id_197>",
|
| 206 |
+
"<extra_id_198>",
|
| 207 |
+
"<extra_id_199>",
|
| 208 |
+
"<extra_id_200>",
|
| 209 |
+
"<extra_id_201>",
|
| 210 |
+
"<extra_id_202>",
|
| 211 |
+
"<extra_id_203>",
|
| 212 |
+
"<extra_id_204>",
|
| 213 |
+
"<extra_id_205>",
|
| 214 |
+
"<extra_id_206>",
|
| 215 |
+
"<extra_id_207>",
|
| 216 |
+
"<extra_id_208>",
|
| 217 |
+
"<extra_id_209>",
|
| 218 |
+
"<extra_id_210>",
|
| 219 |
+
"<extra_id_211>",
|
| 220 |
+
"<extra_id_212>",
|
| 221 |
+
"<extra_id_213>",
|
| 222 |
+
"<extra_id_214>",
|
| 223 |
+
"<extra_id_215>",
|
| 224 |
+
"<extra_id_216>",
|
| 225 |
+
"<extra_id_217>",
|
| 226 |
+
"<extra_id_218>",
|
| 227 |
+
"<extra_id_219>",
|
| 228 |
+
"<extra_id_220>",
|
| 229 |
+
"<extra_id_221>",
|
| 230 |
+
"<extra_id_222>",
|
| 231 |
+
"<extra_id_223>",
|
| 232 |
+
"<extra_id_224>",
|
| 233 |
+
"<extra_id_225>",
|
| 234 |
+
"<extra_id_226>",
|
| 235 |
+
"<extra_id_227>",
|
| 236 |
+
"<extra_id_228>",
|
| 237 |
+
"<extra_id_229>",
|
| 238 |
+
"<extra_id_230>",
|
| 239 |
+
"<extra_id_231>",
|
| 240 |
+
"<extra_id_232>",
|
| 241 |
+
"<extra_id_233>",
|
| 242 |
+
"<extra_id_234>",
|
| 243 |
+
"<extra_id_235>",
|
| 244 |
+
"<extra_id_236>",
|
| 245 |
+
"<extra_id_237>",
|
| 246 |
+
"<extra_id_238>",
|
| 247 |
+
"<extra_id_239>",
|
| 248 |
+
"<extra_id_240>",
|
| 249 |
+
"<extra_id_241>",
|
| 250 |
+
"<extra_id_242>",
|
| 251 |
+
"<extra_id_243>",
|
| 252 |
+
"<extra_id_244>",
|
| 253 |
+
"<extra_id_245>",
|
| 254 |
+
"<extra_id_246>",
|
| 255 |
+
"<extra_id_247>",
|
| 256 |
+
"<extra_id_248>",
|
| 257 |
+
"<extra_id_249>",
|
| 258 |
+
"<extra_id_250>",
|
| 259 |
+
"<extra_id_251>",
|
| 260 |
+
"<extra_id_252>",
|
| 261 |
+
"<extra_id_253>",
|
| 262 |
+
"<extra_id_254>",
|
| 263 |
+
"<extra_id_255>",
|
| 264 |
+
"<extra_id_256>",
|
| 265 |
+
"<extra_id_257>",
|
| 266 |
+
"<extra_id_258>",
|
| 267 |
+
"<extra_id_259>",
|
| 268 |
+
"<extra_id_260>",
|
| 269 |
+
"<extra_id_261>",
|
| 270 |
+
"<extra_id_262>",
|
| 271 |
+
"<extra_id_263>",
|
| 272 |
+
"<extra_id_264>",
|
| 273 |
+
"<extra_id_265>",
|
| 274 |
+
"<extra_id_266>",
|
| 275 |
+
"<extra_id_267>",
|
| 276 |
+
"<extra_id_268>",
|
| 277 |
+
"<extra_id_269>",
|
| 278 |
+
"<extra_id_270>",
|
| 279 |
+
"<extra_id_271>",
|
| 280 |
+
"<extra_id_272>",
|
| 281 |
+
"<extra_id_273>",
|
| 282 |
+
"<extra_id_274>",
|
| 283 |
+
"<extra_id_275>",
|
| 284 |
+
"<extra_id_276>",
|
| 285 |
+
"<extra_id_277>",
|
| 286 |
+
"<extra_id_278>",
|
| 287 |
+
"<extra_id_279>",
|
| 288 |
+
"<extra_id_280>",
|
| 289 |
+
"<extra_id_281>",
|
| 290 |
+
"<extra_id_282>",
|
| 291 |
+
"<extra_id_283>",
|
| 292 |
+
"<extra_id_284>",
|
| 293 |
+
"<extra_id_285>",
|
| 294 |
+
"<extra_id_286>",
|
| 295 |
+
"<extra_id_287>",
|
| 296 |
+
"<extra_id_288>",
|
| 297 |
+
"<extra_id_289>",
|
| 298 |
+
"<extra_id_290>",
|
| 299 |
+
"<extra_id_291>",
|
| 300 |
+
"<extra_id_292>",
|
| 301 |
+
"<extra_id_293>",
|
| 302 |
+
"<extra_id_294>",
|
| 303 |
+
"<extra_id_295>",
|
| 304 |
+
"<extra_id_296>",
|
| 305 |
+
"<extra_id_297>",
|
| 306 |
+
"<extra_id_298>",
|
| 307 |
+
"<extra_id_299>"
|
| 308 |
+
],
|
| 309 |
+
"is_local": false,
|
| 310 |
+
"local_files_only": false,
|
| 311 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 312 |
+
"pad_token": "<pad>",
|
| 313 |
+
"sp_model_kwargs": {},
|
| 314 |
+
"spaces_between_special_tokens": false,
|
| 315 |
+
"tokenizer_class": "T5Tokenizer",
|
| 316 |
+
"unk_token": "<unk>"
|
| 317 |
+
}
|
transformer/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "WanTransformer3DModel",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"added_kv_proj_dim": null,
|
| 5 |
+
"attention_head_dim": 16,
|
| 6 |
+
"cross_attn_norm": true,
|
| 7 |
+
"eps": 1e-06,
|
| 8 |
+
"ffn_dim": 64,
|
| 9 |
+
"freq_dim": 32,
|
| 10 |
+
"image_dim": null,
|
| 11 |
+
"in_channels": 4,
|
| 12 |
+
"num_attention_heads": 2,
|
| 13 |
+
"num_layers": 1,
|
| 14 |
+
"out_channels": 4,
|
| 15 |
+
"patch_size": [
|
| 16 |
+
1,
|
| 17 |
+
2,
|
| 18 |
+
2
|
| 19 |
+
],
|
| 20 |
+
"pos_embed_seq_len": null,
|
| 21 |
+
"qk_norm": "rms_norm_across_heads",
|
| 22 |
+
"rope_max_seq_len": 64,
|
| 23 |
+
"text_dim": 32
|
| 24 |
+
}
|
transformer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a1d4ba7feaeb6a600e87f5c8e0638a6b436a2a0e4414553aa608975b9e993f4
|
| 3 |
+
size 102760
|
transformer_2/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "WanTransformer3DModel",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"added_kv_proj_dim": null,
|
| 5 |
+
"attention_head_dim": 16,
|
| 6 |
+
"cross_attn_norm": true,
|
| 7 |
+
"eps": 1e-06,
|
| 8 |
+
"ffn_dim": 64,
|
| 9 |
+
"freq_dim": 32,
|
| 10 |
+
"image_dim": null,
|
| 11 |
+
"in_channels": 4,
|
| 12 |
+
"num_attention_heads": 2,
|
| 13 |
+
"num_layers": 1,
|
| 14 |
+
"out_channels": 4,
|
| 15 |
+
"patch_size": [
|
| 16 |
+
1,
|
| 17 |
+
2,
|
| 18 |
+
2
|
| 19 |
+
],
|
| 20 |
+
"pos_embed_seq_len": null,
|
| 21 |
+
"qk_norm": "rms_norm_across_heads",
|
| 22 |
+
"rope_max_seq_len": 64,
|
| 23 |
+
"text_dim": 32
|
| 24 |
+
}
|
transformer_2/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d575fe375fb7814a95aed0a44c8d1908bef4ae62d4bba8786b3f538c27a34010
|
| 3 |
+
size 102760
|
vae/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKLWan",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"attn_scales": [],
|
| 5 |
+
"base_dim": 8,
|
| 6 |
+
"decoder_base_dim": 8,
|
| 7 |
+
"dim_mult": [
|
| 8 |
+
1,
|
| 9 |
+
1,
|
| 10 |
+
1,
|
| 11 |
+
1
|
| 12 |
+
],
|
| 13 |
+
"dropout": 0.0,
|
| 14 |
+
"in_channels": 3,
|
| 15 |
+
"is_residual": false,
|
| 16 |
+
"latents_mean": [
|
| 17 |
+
0.0,
|
| 18 |
+
0.0,
|
| 19 |
+
0.0,
|
| 20 |
+
0.0
|
| 21 |
+
],
|
| 22 |
+
"latents_std": [
|
| 23 |
+
1.0,
|
| 24 |
+
1.0,
|
| 25 |
+
1.0,
|
| 26 |
+
1.0
|
| 27 |
+
],
|
| 28 |
+
"num_res_blocks": 1,
|
| 29 |
+
"out_channels": 3,
|
| 30 |
+
"patch_size": null,
|
| 31 |
+
"scale_factor_spatial": 8,
|
| 32 |
+
"scale_factor_temporal": 4,
|
| 33 |
+
"temperal_downsample": [
|
| 34 |
+
false,
|
| 35 |
+
true,
|
| 36 |
+
true
|
| 37 |
+
],
|
| 38 |
+
"z_dim": 4
|
| 39 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58971006ecd31911f6c0eb2f34f2f78f8e8445cfd036e54aa80948adc9e8ffbc
|
| 3 |
+
size 262220
|