Upload QwenImageModularPipeline

modular_model_index.json

@@ -2,8 +2,22 @@
   "_blocks_class_name": "SequentialPipelineBlocks",
   "_class_name": "QwenImageModularPipeline",
   "_diffusers_version": "0.36.0.dev0",
-  "prompt_template_encode": "<|im_start|>system\nDescribe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n",
-  "prompt_template_encode_start_idx": 34,
+  "processor": [
+    "transformers",
+    "Qwen2VLProcessor",
+    {
+      "repo": "hf-internal-testing/tiny-qwenimage-edit-pipe",
+      "revision": null,
+      "subfolder": "processor",
+      "type_hint": [
+        "transformers",
+        "Qwen2VLProcessor"
+      ],
+      "variant": null
+    }
+  ],
+  "prompt_template_encode": "<|im_start|>system\nDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>\n<|im_start|>assistant\n",
+  "prompt_template_encode_start_idx": 64,
   "scheduler": [
     "diffusers",
     "FlowMatchEulerDiscreteScheduler",
@@ -32,21 +46,6 @@
       "variant": null
     }
   ],
-  "tokenizer": [
-    "transformers",
-    "Qwen2Tokenizer",
-    {
-      "repo": "hf-internal-testing/tiny-qwenimage-edit-pipe",
-      "revision": null,
-      "subfolder": "tokenizer",
-      "type_hint": [
-        "transformers",
-        "Qwen2Tokenizer"
-      ],
-      "variant": null
-    }
-  ],
-  "tokenizer_max_length": 1024,
   "transformer": [
     "diffusers",
     "QwenImageTransformer2DModel",