Upload QwenImagePipeline

.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

@@ -1,3 +1,4 @@
 ---
 license: apache-2.0
+library_name: diffusers
 ---

model_index.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "QwenImagePipeline",
+  "_diffusers_version": "0.36.0",
+  "_name_or_path": "hf-internal-testing/tiny-qwenimage-pipe",
+  "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": "0.36.0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,75 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "hidden_size": 16,
+  "model_type": "qwen2_5_vl",
+  "text_config": {
+    "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--hf-internal-testing--tiny-qwenimage-pipe/snapshots/4d1fcf7bbc41fff7f4e686dba11f871a3ad84a09/text_encoder",
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "image_token_id": 151655,
+    "initializer_range": 0.02,
+    "intermediate_size": 16,
+    "layer_types": [
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "max_window_layers": 80,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "mrope_section": [
+        1,
+        1,
+        2
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": 151656,
+    "vocab_size": 152064
+  },
+  "transformers_version": "4.57.3",
+  "vision_config": {
+    "depth": 2,
+    "dtype": "float32",
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 16,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 2,
+    "out_hidden_size": 16,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 4,
+    "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 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.57.3"
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e035ddbd77d8338bbf7ee0b05d8c39f4d7bdbfa891249a0eb28ebea46d43f207
+size 19596672

tokenizer/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

tokenizer/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% 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:e24d28c0a7e2c08dcc0486e3f243ececb8b7c4abf6064fb863f1d0fc92ef9309
+size 11420365

tokenizer/tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "QwenImageTransformer2DModel",
+  "_diffusers_version": "0.36.0",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--hf-internal-testing--tiny-qwenimage-pipe/snapshots/4d1fcf7bbc41fff7f4e686dba11f871a3ad84a09/transformer",
+  "attention_head_dim": 16,
+  "axes_dims_rope": [
+    8,
+    4,
+    4
+  ],
+  "guidance_embeds": false,
+  "in_channels": 16,
+  "joint_attention_dim": 16,
+  "num_attention_heads": 3,
+  "num_layers": 2,
+  "out_channels": 4,
+  "patch_size": 2
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6cbcf17cb395b2e502856f78ad629c9b4595c439f904edf2e1f2d43d2f21f77
+size 770752

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKLQwenImage",
+  "_diffusers_version": "0.36.0",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--hf-internal-testing--tiny-qwenimage-pipe/snapshots/4d1fcf7bbc41fff7f4e686dba11f871a3ad84a09/vae",
+  "attn_scales": [],
+  "base_dim": 24,
+  "dim_mult": [
+    1,
+    2,
+    4
+  ],
+  "dropout": 0.0,
+  "latents_mean": [
+    0.0,
+    0.0,
+    0.0,
+    0.0
+  ],
+  "latents_std": [
+    1.0,
+    1.0,
+    1.0,
+    1.0
+  ],
+  "num_res_blocks": 1,
+  "temperal_downsample": [
+    false,
+    true
+  ],
+  "z_dim": 4
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82f6ac6ca2e5767a17a5efc504e0470705b3b3318bab132dd218ff0ff342d29
+size 16230492