stable diffusion

ldm/modules/encoders/modules.py

@@ -1,6 +1,10 @@
 import torch
 import torch.nn as nn
 from functools import partial
+import clip
+from einops import rearrange, repeat
+from transformers import CLIPTokenizer, CLIPTextModel
+import kornia
 
 from ldm.modules.x_transformer import Encoder, TransformerWrapper  # TODO: can we directly rely on lucidrains code and simply add this as a reuirement? --> test
 
@@ -129,3 +133,102 @@ class SpatialRescaler(nn.Module):
 
     def encode(self, x):
         return self(x)
+
+class FrozenCLIPEmbedder(AbstractEncoder):
+    """Uses the CLIP transformer encoder for text (from Hugging Face)"""
+    def __init__(self, version="openai/clip-vit-large-patch14", device="cuda", max_length=77):
+        super().__init__()
+        self.tokenizer = CLIPTokenizer.from_pretrained(version)
+        self.transformer = CLIPTextModel.from_pretrained(version)
+        self.device = device
+        self.max_length = max_length
+        self.freeze()
+
+    def freeze(self):
+        self.transformer = self.transformer.eval()
+        for param in self.parameters():
+            param.requires_grad = False
+
+    def forward(self, text):
+        batch_encoding = self.tokenizer(text, truncation=True, max_length=self.max_length, return_length=True,
+                                        return_overflowing_tokens=False, padding="max_length", return_tensors="pt")
+        tokens = batch_encoding["input_ids"].to(self.device)
+        outputs = self.transformer(input_ids=tokens)
+
+        z = outputs.last_hidden_state
+        return z
+
+    def encode(self, text):
+        return self(text)
+
+
+class FrozenCLIPTextEmbedder(nn.Module):
+    """
+    Uses the CLIP transformer encoder for text.
+    """
+    def __init__(self, version='ViT-L/14', device="cuda", max_length=77, n_repeat=1, normalize=True):
+        super().__init__()
+        self.model, _ = clip.load(version, jit=False, device="cpu")
+        self.device = device
+        self.max_length = max_length
+        self.n_repeat = n_repeat
+        self.normalize = normalize
+
+    def freeze(self):
+        self.model = self.model.eval()
+        for param in self.parameters():
+            param.requires_grad = False
+
+    def forward(self, text):
+        tokens = clip.tokenize(text).to(self.device)
+        z = self.model.encode_text(tokens)
+        if self.normalize:
+            z = z / torch.linalg.norm(z, dim=1, keepdim=True)
+        return z
+
+    def encode(self, text):
+        z = self(text)
+        if z.ndim==2:
+            z = z[:, None, :]
+        z = repeat(z, 'b 1 d -> b k d', k=self.n_repeat)
+        return z
+
+
+class FrozenClipImageEmbedder(nn.Module):
+    """
+        Uses the CLIP image encoder.
+        """
+    def __init__(
+            self,
+            model,
+            jit=False,
+            device='cuda' if torch.cuda.is_available() else 'cpu',
+            antialias=False,
+        ):
+        super().__init__()
+        self.model, _ = clip.load(name=model, device=device, jit=jit)
+
+        self.antialias = antialias
+
+        self.register_buffer('mean', torch.Tensor([0.48145466, 0.4578275, 0.40821073]), persistent=False)
+        self.register_buffer('std', torch.Tensor([0.26862954, 0.26130258, 0.27577711]), persistent=False)
+
+    def preprocess(self, x):
+        # normalize to [0,1]
+        x = kornia.geometry.resize(x, (224, 224),
+                                   interpolation='bicubic',align_corners=True,
+                                   antialias=self.antialias)
+        x = (x + 1.) / 2.
+        # renormalize according to clip
+        x = kornia.enhance.normalize(x, self.mean, self.std)
+        return x
+
+    def forward(self, x):
+        # x is assumed to be in range [-1,1]
+        return self.model.encode_image(self.preprocess(x))
+
+
+if __name__ == "__main__":
+    from ldm.util import count_params
+    model = FrozenCLIPEmbedder()
+    count_params(model, verbose=True)