Upload folder using huggingface_hub

.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 +1,183 @@
+---
+library_name: Diffusers
+pipeline_tag: text-to-image
+inference: true
+base_model:
+- Qwen/Qwen-Image
+---
+
+This tiny model is for debugging. It is randomly initialized with the config adapted from [Qwen/Qwen-Image](https://huggingface.co/Qwen/Qwen-Image).
+
+File size:
+- ~10MB  text_encoder/model.safetensors
+- ~200KB transformer/diffusion_pytorch_model.safetensors
+- ~5MB   vae/diffusion_pytorch_model.safetensors
+
+### Example usage:
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+model_id = "tiny-random/Qwen-Image"
+torch_dtype = torch.bfloat16
+device = "cuda"
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype)
+pipe = pipe.to(device)
+
+positive_magic = {
+    "en": "Ultra HD, 4K, cinematic composition.",  # for english prompt,
+    "zh": "超清，4K，电影级构图"  # for chinese prompt,
+}
+prompt = '''A coffee shop entrance features a chalkboard sign reading "Qwen Coffee 😊 $2 per cup," with a neon light beside it displaying "通义千问". Next to it hangs a poster showing a beautiful Chinese woman, and beneath the poster is written "π≈3.1415926-53589793-23846264-33832795-02384197". Ultra HD, 4K, cinematic composition.'''
+prompt += 'Some dummy random texts to make prompt long enough ' * 10
+negative_prompt = " "
+
+# Generate with different aspect ratios
+aspect_ratios = {
+    "1:1": (1328, 1328),
+    "16:9": (1664, 928),
+    "9:16": (928, 1664),
+    "4:3": (1472, 1140),
+    "3:4": (1140, 1472)
+}
+
+for width, height in aspect_ratios.values():
+    image = pipe(
+        prompt=prompt + positive_magic["en"],
+        negative_prompt=negative_prompt,
+        width=width,
+        height=height,
+        num_inference_steps=4,
+        true_cfg_scale=4.0,
+        generator=torch.Generator(device="cuda").manual_seed(42)
+    ).images[0]
+    print(image)
+```
+
+### Codes to create this repo:
+
+```python
+import json
+
+import torch
+from diffusers import (
+    AutoencoderKLQwenImage,
+    DiffusionPipeline,
+    FlowMatchEulerDiscreteScheduler,
+    QwenImagePipeline,
+    QwenImageTransformer2DModel,
+)
+from huggingface_hub import hf_hub_download
+from transformers import AutoConfig, AutoTokenizer, Qwen2_5_VLForConditionalGeneration
+from transformers.generation import GenerationConfig
+
+source_model_id = "Qwen/Qwen-Image"
+save_folder = "/tmp/tiny-random/Qwen-Image"
+
+torch.set_default_dtype(torch.bfloat16)
+scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(source_model_id, subfolder='scheduler')
+tokenizer = AutoTokenizer.from_pretrained(source_model_id, subfolder='tokenizer')
+
+def save_json(path, obj):
+    import json
+    from pathlib import Path
+    Path(path).parent.mkdir(parents=True, exist_ok=True)
+    with open(path, 'w', encoding='utf-8') as f:
+        json.dump(obj, f, indent=2, ensure_ascii=False)
+
+def init_weights(model):
+    import torch
+    torch.manual_seed(42)
+    with torch.no_grad():
+        for name, p in sorted(model.named_parameters()):
+            torch.nn.init.normal_(p, 0, 0.3)
+            print(name, p.shape, p.dtype, p.device)
+
+with open(hf_hub_download(source_model_id, filename='text_encoder/config.json', repo_type='model'), 'r', encoding='utf - 8') as f:
+    config = json.load(f)
+    config.update({
+        'hidden_size': 32,
+        'intermediate_size': 64,
+        'max_window_layers': 1,
+        'num_attention_heads': 2,
+        'num_hidden_layers': 2,
+        'num_key_value_heads': 1,
+        'sliding_window': 64,
+        'tie_word_embeddings': True,
+        'use_sliding_window': True,
+    })
+    del config['torch_dtype']
+    config['rope_scaling']['mrope_section'] = [4, 2, 2]
+    config['text_config'].update({
+        'hidden_size': 32,
+        'intermediate_size': 64,
+        'num_attention_heads': 2,
+        'num_hidden_layers': 2,
+        'num_key_value_heads': 1,
+        'sliding_window': 64,
+        'tie_word_embeddings': True,
+        'use_sliding_window': True,
+        'layer_types': ['full_attention', 'sliding_attention']
+    })
+    del config['text_config']['torch_dtype']
+    config['text_config']['rope_scaling']['mrope_section'] = [4, 2, 2]
+    config['vision_config'].update(
+        {
+            'depth': 2,
+            'fullatt_block_indexes': [0],
+            'hidden_size': 32,
+            'intermediate_size': 64,
+            'num_heads': 2,
+            'out_hidden_size': 32,
+        }
+    )
+    del config['vision_config']['torch_dtype']
+    save_json(f'{save_folder}/text_encoder/config.json', config)
+    text_encoder_config = AutoConfig.from_pretrained(f'{save_folder}/text_encoder')
+    text_encoder = Qwen2_5_VLForConditionalGeneration(text_encoder_config).to(torch.bfloat16)
+    generation_config = GenerationConfig.from_pretrained(source_model_id, subfolder='text_encoder')
+    # text_encoder.config.generation_config = generation_config
+    text_encoder.generation_config = generation_config
+    init_weights(text_encoder)
+
+with open(hf_hub_download(source_model_id, filename='transformer/config.json', repo_type='model'), 'r', encoding='utf-8') as f:
+    config = json.load(f)
+    config.update({
+        'attention_head_dim': 32,
+        'axes_dims_rope': [8, 12, 12],
+        'joint_attention_dim': 32,
+        'num_attention_heads': 1,
+        'num_layers': 2,
+    })
+    del config['pooled_projection_dim']  # not used
+    save_json(f'{save_folder}/transformer/config.json', config)
+    transformer_config = QwenImageTransformer2DModel.load_config(f'{save_folder}/transformer')
+    transformer = QwenImageTransformer2DModel.from_config(transformer_config)
+    init_weights(transformer)
+
+with open(hf_hub_download(source_model_id, filename='vae/config.json', repo_type='model'), 'r', encoding='utf-8') as f:
+    config = json.load(f)
+    config.update({
+        'num_res_blocks': 1,
+        'base_dim': 16,
+        'dim_mult': [1, 2, 4, 4],
+    })
+    del config['latents_mean']  # not used
+    del config['latents_std']  # not used
+    save_json(f'{save_folder}/vae/config.json', config)
+    vae_config = AutoencoderKLQwenImage.load_config(f'{save_folder}/vae')
+    vae = AutoencoderKLQwenImage.from_config(vae_config)
+    init_weights(vae)
+
+pipeline = QwenImagePipeline(
+    scheduler=scheduler,
+    text_encoder=text_encoder,
+    tokenizer=tokenizer,
+    transformer=transformer,
+    vae=vae,
+)
+pipeline = pipeline.to(torch.bfloat16)
+pipeline.save_pretrained(save_folder, safe_serialization=True)
+print(pipeline)
+```

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "QwenImagePipeline",
+  "_diffusers_version": "0.35.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "QwenImageTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLQwenImage"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.35.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 8192,
+  "max_shift": 0.9,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": 0.02,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,104 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 1,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      4,
+      2,
+      2
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 64,
+  "text_config": {
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_types": [
+      "full_attention",
+      "sliding_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        4,
+        2,
+        2
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 64,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "use_sliding_window": true,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": true,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 2,
+    "fullatt_block_indexes": [
+      0
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 2,
+    "out_hidden_size": 32,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

text_encoder/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.55.0.dev0"
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e3ebc942572273af5e8c8f17a785d002c39f6bb474877509a23f9e3c539372
+size 9934200

tokenizer/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

tokenizer/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tokenizer/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae8594f633daa21dc0e04606279856d0ccb8abb64bb7a5a93e72531fb12b9d9
+size 11421890

tokenizer/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,17 @@
+{
+  "_class_name": "QwenImageTransformer2DModel",
+  "_diffusers_version": "0.35.0.dev0",
+  "attention_head_dim": 32,
+  "axes_dims_rope": [
+    8,
+    12,
+    12
+  ],
+  "guidance_embeds": false,
+  "in_channels": 64,
+  "joint_attention_dim": 32,
+  "num_attention_heads": 1,
+  "num_layers": 2,
+  "out_channels": 16,
+  "patch_size": 2
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d395479784afe4b1ad9674bb414a48772e5f7c4469cb70a46b1dce2c10d00aa
+size 193040

vae/config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "AutoencoderKLQwenImage",
+  "_diffusers_version": "0.35.0.dev0",
+  "attn_scales": [],
+  "base_dim": 16,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "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": 1,
+  "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 sha256:60f741a6bb83745a07da3d0793fd21b99146baa0519cd777f35da947d3eb0032
+size 5171798