backend

ldm_patched/contrib/external.py

@@ -361,6 +361,62 @@ class VAEEncodeForInpaint:
 
         return ({"samples":t, "noise_mask": (mask_erosion[:,:,:x,:y].round())}, )
 
+
+class InpaintModelConditioning:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {"positive": ("CONDITIONING", ),
+                             "negative": ("CONDITIONING", ),
+                             "vae": ("VAE", ),
+                             "pixels": ("IMAGE", ),
+                             "mask": ("MASK", ),
+                             }}
+
+    RETURN_TYPES = ("CONDITIONING","CONDITIONING","LATENT")
+    RETURN_NAMES = ("positive", "negative", "latent")
+    FUNCTION = "encode"
+
+    CATEGORY = "conditioning/inpaint"
+
+    def encode(self, positive, negative, pixels, vae, mask):
+        x = (pixels.shape[1] // 8) * 8
+        y = (pixels.shape[2] // 8) * 8
+        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(pixels.shape[1], pixels.shape[2]), mode="bilinear")
+
+        orig_pixels = pixels
+        pixels = orig_pixels.clone()
+        if pixels.shape[1] != x or pixels.shape[2] != y:
+            x_offset = (pixels.shape[1] % 8) // 2
+            y_offset = (pixels.shape[2] % 8) // 2
+            pixels = pixels[:,x_offset:x + x_offset, y_offset:y + y_offset,:]
+            mask = mask[:,:,x_offset:x + x_offset, y_offset:y + y_offset]
+
+        m = (1.0 - mask.round()).squeeze(1)
+        for i in range(3):
+            pixels[:,:,:,i] -= 0.5
+            pixels[:,:,:,i] *= m
+            pixels[:,:,:,i] += 0.5
+        concat_latent = vae.encode(pixels)
+        orig_latent = vae.encode(orig_pixels)
+
+        out_latent = {}
+
+        out_latent["samples"] = orig_latent
+        out_latent["noise_mask"] = mask
+
+        out = []
+        for conditioning in [positive, negative]:
+            c = []
+            for t in conditioning:
+                d = t[1].copy()
+                d["concat_latent_image"] = concat_latent
+                d["concat_mask"] = mask
+                n = [t[0], d]
+                c.append(n)
+            out.append(c)
+        return (out[0], out[1], out_latent)
+
+
 class SaveLatent:
     def __init__(self):
         self.output_dir = ldm_patched.utils.path_utils.get_output_directory()
@@ -1417,6 +1473,8 @@ class LoadImage:
         output_masks = []
         for i in ImageSequence.Iterator(img):
             i = ImageOps.exif_transpose(i)
+            if i.mode == 'I':
+                i = i.point(lambda i: i * (1 / 255))
             image = i.convert("RGB")
             image = np.array(image).astype(np.float32) / 255.0
             image = torch.from_numpy(image)[None,]
@@ -1472,6 +1530,8 @@ class LoadImageMask:
         i = Image.open(image_path)
         i = ImageOps.exif_transpose(i)
         if i.getbands() != ("R", "G", "B", "A"):
+            if i.mode == 'I':
+                i = i.point(lambda i: i * (1 / 255))
             i = i.convert("RGBA")
         mask = None
         c = channel[0].upper()
@@ -1626,10 +1686,11 @@ class ImagePadForOutpaint:
     def expand_image(self, image, left, top, right, bottom, feathering):
         d1, d2, d3, d4 = image.size()
 
-        new_image = torch.zeros(
+        new_image = torch.ones(
             (d1, d2 + top + bottom, d3 + left + right, d4),
             dtype=torch.float32,
-        )
+        ) * 0.5
+
         new_image[:, top:top + d2, left:left + d3, :] = image
 
         mask = torch.ones(
@@ -1721,6 +1782,7 @@ NODE_CLASS_MAPPINGS = {
     "unCLIPCheckpointLoader": unCLIPCheckpointLoader,
     "GLIGENLoader": GLIGENLoader,
     "GLIGENTextBoxApply": GLIGENTextBoxApply,
+    "InpaintModelConditioning": InpaintModelConditioning,
 
     "CheckpointLoader": CheckpointLoader,
     "DiffusersLoader": DiffusersLoader,
@@ -1882,6 +1944,8 @@ def init_custom_nodes():
         "nodes_sag.py",
         "nodes_perpneg.py",
         "nodes_stable3d.py",
+        "nodes_sdupscale.py",
+        "nodes_photomaker.py",
     ]
 
     for node_file in extras_files: