.

main.py

@@ -224,6 +224,8 @@ def predict_next_frame(previous_frames: List[np.ndarray], previous_actions: List
     prev_y = 0
     #print ('here')
 
+    prompt = 'N + 0 2 4 0 : + 0 0 3 2 N + 0 1 6 0 : + 0 0 2 4 N + 0 1 9 2 : + 0 0 9 6 N + 0 1 1 2 : + 0 0 9 6 N + 0 1 5 2 : + 0 1 7 6 N + 0 0 0 0 : + 0 2 3 2 N + 0 3 2 0 : + 0 2 7 2 N + 0 4 6 4 : + 0 3 2 8'
+    previous_actions = [('move', (240, 32)), ('move', (160, 24)), ('move', (192, 96)), ('move', (112, 96)), ('move', (152, 176)), ('move', (0, 232)), ('move', (320, 272)), ('move', (464, 328))]
     
     
     for action_type, pos in previous_actions: #[-8:]:

utils.py

@@ -38,6 +38,9 @@ def sample_frame(model: LatentDiffusion, prompt: str, image_sequence: torch.Tens
         
         c_dict = {'c_crossattn': prompt, 'c_concat': image_sequence}
         c = model.get_learned_conditioning(c_dict)
+        print (c['c_crossattn'].shape)
+        print (c['c_crossattn'][0])
+        print (prompt)
         c = model.enc_concat_seq(c, c_dict, 'c_concat')
         # Zero out the corresponding subtensors in c_concat for padding images
         padding_mask = torch.isclose(image_sequence, torch.tensor(-1.0), rtol=1e-5, atol=1e-5).all(dim=(1, 2, 3)).unsqueeze(0)