diff --git a/esphome/components/animation/__init__.py b/esphome/components/animation/__init__.py
index 87d72254e8..ce9f057496 100644
--- a/esphome/components/animation/__init__.py
+++ b/esphome/components/animation/__init__.py
@@ -117,7 +117,7 @@ async def to_code(config):
                 data[pos] = rgb & 255
                 pos += 1
 
-    elif config[CONF_TYPE] == "BINARY":
+    elif config[CONF_TYPE] in ["BINARY", "TRANSPARENT_BINARY"]:
         width8 = ((width + 7) // 8) * 8
         data = [0 for _ in range((height * width8 // 8) * frames)]
         for frameIndex in range(frames):
diff --git a/esphome/components/display/display_buffer.cpp b/esphome/components/display/display_buffer.cpp
index 97c08dae24..cfd73509ea 100644
--- a/esphome/components/display/display_buffer.cpp
+++ b/esphome/components/display/display_buffer.cpp
@@ -452,7 +452,7 @@ int Font::match_next_glyph(const char *str, int *match_length) {
 }
 void Font::measure(const char *str, int *width, int *x_offset, int *baseline, int *height) {
   *baseline = this->baseline_;
-  *height = this->bottom_;
+  *height = this->height_;
   int i = 0;
   int min_x = 0;
   bool has_char = false;
@@ -483,7 +483,7 @@ void Font::measure(const char *str, int *width, int *x_offset, int *baseline, in
   *width = x - min_x;
 }
 const std::vector<Glyph> &Font::get_glyphs() const { return this->glyphs_; }
-Font::Font(const GlyphData *data, int data_nr, int baseline, int bottom) : baseline_(baseline), bottom_(bottom) {
+Font::Font(const GlyphData *data, int data_nr, int baseline, int height) : baseline_(baseline), height_(height) {
   for (int i = 0; i < data_nr; ++i)
     glyphs_.emplace_back(data + i);
 }
@@ -527,6 +527,7 @@ int Image::get_height() const { return this->height_; }
 ImageType Image::get_type() const { return this->type_; }
 Image::Image(const uint8_t *data_start, int width, int height, ImageType type)
     : width_(width), height_(height), type_(type), data_start_(data_start) {}
+int Image::get_current_frame() const { return 0; }
 
 bool Animation::get_pixel(int x, int y) const {
   if (x < 0 || x >= this->width_ || y < 0 || y >= this->height_)
diff --git a/esphome/components/display/display_buffer.h b/esphome/components/display/display_buffer.h
index 41052b3ffd..b652989067 100644
--- a/esphome/components/display/display_buffer.h
+++ b/esphome/components/display/display_buffer.h
@@ -448,18 +448,20 @@ class Font {
    * @param baseline The y-offset from the top of the text to the baseline.
    * @param bottom The y-offset from the top of the text to the bottom (i.e. height).
    */
-  Font(const GlyphData *data, int data_nr, int baseline, int bottom);
+  Font(const GlyphData *data, int data_nr, int baseline, int height);
 
   int match_next_glyph(const char *str, int *match_length);
 
   void measure(const char *str, int *width, int *x_offset, int *baseline, int *height);
+  inline int get_baseline() { return this->baseline_; }
+  inline int get_height() { return this->height_; }
 
   const std::vector<Glyph> &get_glyphs() const;
 
  protected:
   std::vector<Glyph> glyphs_;
   int baseline_;
-  int bottom_;
+  int height_;
 };
 
 class Image {
@@ -473,6 +475,8 @@ class Image {
   int get_height() const;
   ImageType get_type() const;
 
+  virtual int get_current_frame() const;
+
  protected:
   int width_;
   int height_;
@@ -489,7 +493,7 @@ class Animation : public Image {
   Color get_grayscale_pixel(int x, int y) const override;
 
   int get_animation_frame_count() const;
-  int get_current_frame() const;
+  int get_current_frame() const override;
   void next_frame();
   void prev_frame();
 
diff --git a/esphome/components/image/__init__.py b/esphome/components/image/__init__.py
index 0004391f20..88c625961b 100644
--- a/esphome/components/image/__init__.py
+++ b/esphome/components/image/__init__.py
@@ -26,6 +26,7 @@ IMAGE_TYPE = {
     "RGB24": ImageType.IMAGE_TYPE_RGB24,
     "TRANSPARENT_BINARY": ImageType.IMAGE_TYPE_TRANSPARENT_BINARY,
     "RGB565": ImageType.IMAGE_TYPE_RGB565,
+    "TRANSPARENT_IMAGE": ImageType.IMAGE_TYPE_TRANSPARENT_BINARY,
 }
 
 Image_ = display.display_ns.class_("Image")
@@ -105,7 +106,7 @@ async def to_code(config):
             data[pos] = rgb & 255
             pos += 1
 
-    elif config[CONF_TYPE] == "BINARY":
+    elif (config[CONF_TYPE] == "BINARY") or (config[CONF_TYPE] == "TRANSPARENT_BINARY"):
         image = image.convert("1", dither=dither)
         width8 = ((width + 7) // 8) * 8
         data = [0 for _ in range(height * width8 // 8)]
@@ -116,7 +117,7 @@ async def to_code(config):
                 pos = x + y * width8
                 data[pos // 8] |= 0x80 >> (pos % 8)
 
-    elif config[CONF_TYPE] == "TRANSPARENT_BINARY":
+    elif config[CONF_TYPE] == "TRANSPARENT_IMAGE":
         image = image.convert("RGBA")
         width8 = ((width + 7) // 8) * 8
         data = [0 for _ in range(height * width8 // 8)]