Upload pipeline_ltx_video.py

pipeline_ltx_video.py

@@ -24,6 +24,15 @@ from transformers import (
     AutoTokenizer,
 )
 
+
+from huggingface_hub import logging
+
+
+logging.set_verbosity_error()
+logging.set_verbosity_warning()
+logging.set_verbosity_info()
+logging.set_verbosity_debug()
+
 from ltx_video.models.autoencoders.causal_video_autoencoder import (
     CausalVideoAutoencoder,
 )
@@ -45,7 +54,8 @@ from ltx_video.models.autoencoders.vae_encode import (
 )
 
 
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
+logger = logging.getlogger(__name__)  
+
 
 
 ASPECT_RATIO_1024_BIN = {
@@ -923,6 +933,9 @@ class LTXVideoPipeline(DiffusionPipeline):
             latent_height,
             latent_width,
         )
+        
+        print(f"[ltxxxxxxxx] latent_shape {latent_shape.shplape}")
+      
 
         # Prepare the list of denoising time-steps
 
@@ -971,7 +984,7 @@ class LTXVideoPipeline(DiffusionPipeline):
             # Cria um mapeamento de identidade seguro.
             guidance_mapping = list(range(len(timesteps)))
             
-            
+        print(f"[ltxxxxxxxx] guidance_mapping {guidance_mapping}")
             
         # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
         # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
@@ -1088,6 +1101,8 @@ class LTXVideoPipeline(DiffusionPipeline):
             generator=generator,
             vae_per_channel_normalize=vae_per_channel_normalize,
         )
+        
+        
 
         # Update the latents with the conditioning items and patchify them into (b, n, c)
         latents, pixel_coords, conditioning_mask, num_cond_latents = (