set separate_cfg_infer=True

app.py

@@ -26,10 +26,10 @@ def generate_image(text, img1, img2, img3, height, width, guidance_scale, img_gu
         guidance_scale=guidance_scale,
         img_guidance_scale=1.6,
         num_inference_steps=inference_steps,
-        # separate_cfg_infer=True, # set False can speed up the inference process
+        separate_cfg_infer=True, # set False can speed up the inference process
         use_kv_cache=False,
         seed=seed,
-        separate_cfg_infer=separate_cfg_infer,
+        # separate_cfg_infer=separate_cfg_infer,
     )
     img = output[0]
     return img
@@ -58,7 +58,7 @@ def get_example():
             1.6,
             50,
             0,
-            False,
+            True,
         ],
         [
             "The woman in <img><|image_1|></img> waves her hand happily in the crowd",
@@ -71,7 +71,7 @@ def get_example():
             1.9,
             50,
             128,
-            False,
+            True,
         ],
         [
             "A man in a black shirt is reading a book. The man is the right man in <img><|image_1|></img>.",
@@ -84,7 +84,7 @@ def get_example():
             1.6,
             50,
             0,
-            False,
+            True,
         ],
         [
             "Two woman are raising fried chicken legs in a bar. A woman is <img><|image_1|></img>. The other woman is <img><|image_2|></img>.",
@@ -97,7 +97,7 @@ def get_example():
             1.8,
             50,
             168,
-            False,
+            True,
         ],
         [
             "A man and a short-haired woman with a wrinkled face are standing in front of a bookshelf in a library. The man is the man in the middle of <img><|image_1|></img>, and the woman is oldest woman in <img><|image_2|></img>",
@@ -110,7 +110,7 @@ def get_example():
             1.6,
             50,
             60,
-            False,
+            True,
         ],
         [
             "A man and a woman are sitting at a classroom desk. The man is the man with yellow hair in <img><|image_1|></img>. The woman is the woman on the left of <img><|image_2|></img>",
@@ -123,7 +123,7 @@ def get_example():
             1.8,
             50,
             66,
-            False,
+            True,
         ],
         [
             "The flower <img><|image_1|><\/img> is placed in the vase which is in the middle of <img><|image_2|><\/img> on a wooden table of a living room",
@@ -136,7 +136,7 @@ def get_example():
             1.6,
             50,
             0,
-            False,
+            True,
         ],
         [
             "<img><|image_1|><img>\n Remove the woman's earrings. Replace the mug with a clear glass filled with sparkling iced cola.",
@@ -149,7 +149,7 @@ def get_example():
             1.6,
             50,
             222,
-            False,
+            True,
         ],
         [
             "Detect the skeleton of human in this image: <img><|image_1|></img>.",
@@ -162,7 +162,7 @@ def get_example():
             1.6,
             50,
             0,
-            False,
+            True,
         ],
         [
             "Generate a new photo using the following picture and text as conditions: <img><|image_1|><img>\n A young boy is sitting on a sofa in the library, holding a book. His hair is neatly combed, and a faint smile plays on his lips, with a few freckles scattered across his cheeks. The library is quiet, with rows of shelves filled with books stretching out behind him.",
@@ -175,7 +175,7 @@ def get_example():
             1.6,
             50,
             42,
-            False,
+            True,
         ],
         [
             "Following the pose of this image <img><|image_1|><img>, generate a new photo: A young boy is sitting on a sofa in the library, holding a book. His hair is neatly combed, and a faint smile plays on his lips, with a few freckles scattered across his cheeks. The library is quiet, with rows of shelves filled with books stretching out behind him.",
@@ -188,7 +188,7 @@ def get_example():
             1.6,
             50,
             123,
-            False,
+            True,
         ],
         [
             "Following the depth mapping of this image <img><|image_1|><img>, generate a new photo: A young girl is sitting on a sofa in the library, holding a book. His hair is neatly combed, and a faint smile plays on his lips, with a few freckles scattered across his cheeks. The library is quiet, with rows of shelves filled with books stretching out behind him.",
@@ -201,7 +201,7 @@ def get_example():
             1.6,
             50,
             1,
-            False,
+            True,
         ],
         [
             "<img><|image_1|><\/img> What item can be used to see the current time? Please remove it.",
@@ -214,7 +214,7 @@ def get_example():
             1.6,
             50,
             0,
-            False,
+            True,
         ],
         [
             "According to the following examples, generate an output for the input.\nInput: <img><|image_1|></img>\nOutput: <img><|image_2|></img>\n\nInput: <img><|image_3|></img>\nOutput: ",
@@ -227,7 +227,7 @@ def get_example():
             1.6,
             50,
             1,
-            False,
+            True,
         ],
     ]
     return case