Upload WanVACEPipeline

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,198 @@
+---
+library_name: diffusers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

model_index.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "WanVACEPipeline",
+  "_diffusers_version": "0.36.0",
+  "boundary_ratio": null,
+  "scheduler": [
+    "diffusers",
+    "UniPCMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "T5EncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "T5Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "WanVACETransformer3DModel"
+  ],
+  "transformer_2": [
+    null,
+    null
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLWan"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "UniPCMultistepScheduler",
+  "_diffusers_version": "0.36.0",
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "beta_start": 0.0001,
+  "disable_corrector": [],
+  "dynamic_thresholding_ratio": 0.995,
+  "final_sigmas_type": "zero",
+  "flow_shift": 3.0,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "predict_x0": true,
+  "prediction_type": "flow_prediction",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "solver_order": 2,
+  "solver_p": null,
+  "solver_type": "bh2",
+  "steps_offset": 0,
+  "thresholding": false,
+  "time_shift_type": "exponential",
+  "timestep_spacing": "linspace",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_flow_sigmas": true,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "scalable_attention": true,
+  "scale_decoder_outputs": false,
+  "tie_word_embeddings": true,
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vocab_size": 256384
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:564f1c2f3a2bd7fca22c2a4ce31491606d234339f48ad47b70ece15eaea65bab
+size 5983718903

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87c960c36d5fbf4e7e76c2469b7eab877be7f8c5992efbf97e44d3123cc6521
+size 16837418

tokenizer/tokenizer_config.json

@@ -0,0 +1,317 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 300,
+  "extra_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>",
+    "<extra_id_100>",
+    "<extra_id_101>",
+    "<extra_id_102>",
+    "<extra_id_103>",
+    "<extra_id_104>",
+    "<extra_id_105>",
+    "<extra_id_106>",
+    "<extra_id_107>",
+    "<extra_id_108>",
+    "<extra_id_109>",
+    "<extra_id_110>",
+    "<extra_id_111>",
+    "<extra_id_112>",
+    "<extra_id_113>",
+    "<extra_id_114>",
+    "<extra_id_115>",
+    "<extra_id_116>",
+    "<extra_id_117>",
+    "<extra_id_118>",
+    "<extra_id_119>",
+    "<extra_id_120>",
+    "<extra_id_121>",
+    "<extra_id_122>",
+    "<extra_id_123>",
+    "<extra_id_124>",
+    "<extra_id_125>",
+    "<extra_id_126>",
+    "<extra_id_127>",
+    "<extra_id_128>",
+    "<extra_id_129>",
+    "<extra_id_130>",
+    "<extra_id_131>",
+    "<extra_id_132>",
+    "<extra_id_133>",
+    "<extra_id_134>",
+    "<extra_id_135>",
+    "<extra_id_136>",
+    "<extra_id_137>",
+    "<extra_id_138>",
+    "<extra_id_139>",
+    "<extra_id_140>",
+    "<extra_id_141>",
+    "<extra_id_142>",
+    "<extra_id_143>",
+    "<extra_id_144>",
+    "<extra_id_145>",
+    "<extra_id_146>",
+    "<extra_id_147>",
+    "<extra_id_148>",
+    "<extra_id_149>",
+    "<extra_id_150>",
+    "<extra_id_151>",
+    "<extra_id_152>",
+    "<extra_id_153>",
+    "<extra_id_154>",
+    "<extra_id_155>",
+    "<extra_id_156>",
+    "<extra_id_157>",
+    "<extra_id_158>",
+    "<extra_id_159>",
+    "<extra_id_160>",
+    "<extra_id_161>",
+    "<extra_id_162>",
+    "<extra_id_163>",
+    "<extra_id_164>",
+    "<extra_id_165>",
+    "<extra_id_166>",
+    "<extra_id_167>",
+    "<extra_id_168>",
+    "<extra_id_169>",
+    "<extra_id_170>",
+    "<extra_id_171>",
+    "<extra_id_172>",
+    "<extra_id_173>",
+    "<extra_id_174>",
+    "<extra_id_175>",
+    "<extra_id_176>",
+    "<extra_id_177>",
+    "<extra_id_178>",
+    "<extra_id_179>",
+    "<extra_id_180>",
+    "<extra_id_181>",
+    "<extra_id_182>",
+    "<extra_id_183>",
+    "<extra_id_184>",
+    "<extra_id_185>",
+    "<extra_id_186>",
+    "<extra_id_187>",
+    "<extra_id_188>",
+    "<extra_id_189>",
+    "<extra_id_190>",
+    "<extra_id_191>",
+    "<extra_id_192>",
+    "<extra_id_193>",
+    "<extra_id_194>",
+    "<extra_id_195>",
+    "<extra_id_196>",
+    "<extra_id_197>",
+    "<extra_id_198>",
+    "<extra_id_199>",
+    "<extra_id_200>",
+    "<extra_id_201>",
+    "<extra_id_202>",
+    "<extra_id_203>",
+    "<extra_id_204>",
+    "<extra_id_205>",
+    "<extra_id_206>",
+    "<extra_id_207>",
+    "<extra_id_208>",
+    "<extra_id_209>",
+    "<extra_id_210>",
+    "<extra_id_211>",
+    "<extra_id_212>",
+    "<extra_id_213>",
+    "<extra_id_214>",
+    "<extra_id_215>",
+    "<extra_id_216>",
+    "<extra_id_217>",
+    "<extra_id_218>",
+    "<extra_id_219>",
+    "<extra_id_220>",
+    "<extra_id_221>",
+    "<extra_id_222>",
+    "<extra_id_223>",
+    "<extra_id_224>",
+    "<extra_id_225>",
+    "<extra_id_226>",
+    "<extra_id_227>",
+    "<extra_id_228>",
+    "<extra_id_229>",
+    "<extra_id_230>",
+    "<extra_id_231>",
+    "<extra_id_232>",
+    "<extra_id_233>",
+    "<extra_id_234>",
+    "<extra_id_235>",
+    "<extra_id_236>",
+    "<extra_id_237>",
+    "<extra_id_238>",
+    "<extra_id_239>",
+    "<extra_id_240>",
+    "<extra_id_241>",
+    "<extra_id_242>",
+    "<extra_id_243>",
+    "<extra_id_244>",
+    "<extra_id_245>",
+    "<extra_id_246>",
+    "<extra_id_247>",
+    "<extra_id_248>",
+    "<extra_id_249>",
+    "<extra_id_250>",
+    "<extra_id_251>",
+    "<extra_id_252>",
+    "<extra_id_253>",
+    "<extra_id_254>",
+    "<extra_id_255>",
+    "<extra_id_256>",
+    "<extra_id_257>",
+    "<extra_id_258>",
+    "<extra_id_259>",
+    "<extra_id_260>",
+    "<extra_id_261>",
+    "<extra_id_262>",
+    "<extra_id_263>",
+    "<extra_id_264>",
+    "<extra_id_265>",
+    "<extra_id_266>",
+    "<extra_id_267>",
+    "<extra_id_268>",
+    "<extra_id_269>",
+    "<extra_id_270>",
+    "<extra_id_271>",
+    "<extra_id_272>",
+    "<extra_id_273>",
+    "<extra_id_274>",
+    "<extra_id_275>",
+    "<extra_id_276>",
+    "<extra_id_277>",
+    "<extra_id_278>",
+    "<extra_id_279>",
+    "<extra_id_280>",
+    "<extra_id_281>",
+    "<extra_id_282>",
+    "<extra_id_283>",
+    "<extra_id_284>",
+    "<extra_id_285>",
+    "<extra_id_286>",
+    "<extra_id_287>",
+    "<extra_id_288>",
+    "<extra_id_289>",
+    "<extra_id_290>",
+    "<extra_id_291>",
+    "<extra_id_292>",
+    "<extra_id_293>",
+    "<extra_id_294>",
+    "<extra_id_295>",
+    "<extra_id_296>",
+    "<extra_id_297>",
+    "<extra_id_298>",
+    "<extra_id_299>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

transformer/config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "WanVACETransformer3DModel",
+  "_diffusers_version": "0.36.0",
+  "_name_or_path": "Wan-AI/Wan2.1-VACE-1.3B-diffusers",
+  "added_kv_proj_dim": null,
+  "attention_head_dim": 128,
+  "cross_attn_norm": true,
+  "eps": 1e-06,
+  "ffn_dim": 8960,
+  "freq_dim": 256,
+  "image_dim": null,
+  "in_channels": 16,
+  "num_attention_heads": 12,
+  "num_layers": 30,
+  "out_channels": 16,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "pos_embed_seq_len": null,
+  "qk_norm": "rms_norm_across_heads",
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rope_max_seq_len": 1024,
+  "text_dim": 4096,
+  "vace_in_channels": 96,
+  "vace_layers": [
+    0,
+    2,
+    4,
+    6,
+    8,
+    10,
+    12,
+    14,
+    16,
+    18,
+    20,
+    22,
+    24,
+    26,
+    28
+  ]
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb7e251975b4a4d8a8fd1824b70d0d8846f0758b744bc16daa2936a622a9d67
+size 1126700088

vae/config.json

@@ -0,0 +1,64 @@
+{
+  "_class_name": "AutoencoderKLWan",
+  "_diffusers_version": "0.36.0",
+  "_name_or_path": "Wan-AI/Wan2.1-VACE-1.3B-diffusers",
+  "attn_scales": [],
+  "base_dim": 96,
+  "decoder_base_dim": null,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "in_channels": 3,
+  "is_residual": false,
+  "latents_mean": [
+    -0.7571,
+    -0.7089,
+    -0.9113,
+    0.1075,
+    -0.1745,
+    0.9653,
+    -0.1517,
+    1.5508,
+    0.4134,
+    -0.0715,
+    0.5517,
+    -0.3632,
+    -0.1922,
+    -0.9497,
+    0.2503,
+    -0.2921
+  ],
+  "latents_std": [
+    2.8184,
+    1.4541,
+    2.3275,
+    2.6558,
+    1.2196,
+    1.7708,
+    2.6052,
+    2.0743,
+    3.2687,
+    2.1526,
+    2.8652,
+    1.5579,
+    1.6382,
+    1.1253,
+    2.8251,
+    1.916
+  ],
+  "num_res_blocks": 2,
+  "out_channels": 3,
+  "patch_size": null,
+  "scale_factor_spatial": 8,
+  "scale_factor_temporal": 4,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 16
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96fa07bac5d2ec749cc74593c0c1ffce88db2c4fd8652009fe8e6a9cd15b703
+size 253806774