diff --git a/server/text_generation_server/models/custom_modeling/qwen2_vl.py b/server/text_generation_server/models/custom_modeling/qwen2_vl.py
index ddb4e36d849..a8e1e8c1593 100644
--- a/server/text_generation_server/models/custom_modeling/qwen2_vl.py
+++ b/server/text_generation_server/models/custom_modeling/qwen2_vl.py
@@ -450,7 +450,7 @@ def get_position_ids(
                     width //= self.spatial_merge_size
 
                     # calculate the length of the text and image tokens
-                    text_length = next_image_pos - current_pos
+                    text_length = next_image_pos
                     start_idx = (
                         llm_pos_ids_list[-1].max() + 1 if llm_pos_ids_list else 0
                     )
@@ -480,7 +480,7 @@ def get_position_ids(
                     )
                     llm_pos_ids_list.append(image_pos_ids)
 
-                    current_pos = next_image_pos + time_steps * height * width
+                    current_pos += next_image_pos + time_steps * height * width
                     image_index += 1
 
             if current_pos < batch_input_ids.size(1):
diff --git a/server/text_generation_server/models/vlm_causal_lm.py b/server/text_generation_server/models/vlm_causal_lm.py
index aa0fe1078d3..81b4369b986 100644
--- a/server/text_generation_server/models/vlm_causal_lm.py
+++ b/server/text_generation_server/models/vlm_causal_lm.py
@@ -68,7 +68,8 @@ def image_text_replacement(processor, image_input, config, image_id: int) -> str
     elif config.model_type == "paligemma":
         return "<image>" * config.text_config.num_image_tokens
     elif config.model_type == "qwen2_vl":
-        num_pads = image_input.pixel_values.shape[0] // 4
+        grid_t, grid_h, grid_w = image_input["image_grid_thw"][image_id]
+        num_pads = grid_t * grid_h * grid_w // 4
         padding = "<|image_pad|>" * num_pads
         return f"<|vision_start|>{padding}<|vision_end|>"
     else: