From 72c6ad996a2cacc8aa72ba5ab25765334a178e4b Mon Sep 17 00:00:00 2001
From: kijai <40791699+kijai@users.noreply.github.com>
Date: Wed, 7 Aug 2024 12:01:10 +0300
Subject: [PATCH] Use main diffusers 0.30.0

---
 examples/cogvideo_vid2vid_test_example_01.json |  4 ++--
 examples/example_01.json                       |  2 +-
 nodes.py                                       | 13 ++++++++-----
 readme.md                                      |  4 +---
 requirements.txt                               |  2 +-
 5 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/examples/cogvideo_vid2vid_test_example_01.json b/examples/cogvideo_vid2vid_test_example_01.json
index fb4b6e5..2416c9d 100644
--- a/examples/cogvideo_vid2vid_test_example_01.json
+++ b/examples/cogvideo_vid2vid_test_example_01.json
@@ -130,7 +130,7 @@
         "Node name for S&R": "CogVideoTextEncode"
       },
       "widgets_values": [
-        "bad quality video, blurry, messy"
+        ""
       ]
     },
     {
@@ -163,7 +163,7 @@
         "Node name for S&R": "DownloadAndLoadCogVideoModel"
       },
       "widgets_values": [
-        "fp16"
+        "bf16"
       ]
     },
     {
diff --git a/examples/example_01.json b/examples/example_01.json
index 1881508..29a854f 100644
--- a/examples/example_01.json
+++ b/examples/example_01.json
@@ -285,7 +285,7 @@
         "Node name for S&R": "DownloadAndLoadCogVideoModel"
       },
       "widgets_values": [
-        "fp16"
+        "bf16"
       ]
     },
     {
diff --git a/nodes.py b/nodes.py
index 9239618..dc3bf73 100644
--- a/nodes.py
+++ b/nodes.py
@@ -2,6 +2,7 @@ import os
 import torch
 import folder_paths
 import comfy.model_management as mm
+from comfy.utils import ProgressBar
 from diffusers.schedulers import CogVideoXDDIMScheduler, CogVideoXDPMScheduler
 from diffusers.models import AutoencoderKLCogVideoX, CogVideoXTransformer3DModel
 from .pipeline_cogvideox import CogVideoXPipeline
@@ -24,7 +25,7 @@ class DownloadAndLoadCogVideoModel:
                         "fp32",
                         "bf16",
                     ],
-                    {"default": "fp16"},
+                    {"default": "bf16"},
                 ),
             },
         }
@@ -286,14 +287,16 @@ class CogVideoDecode:
         latents = 1 / vae.config.scaling_factor * latents
 
         frames = []
+        pbar = ProgressBar(num_seconds)
         for i in range(num_seconds):
-            # Whether or not to clear fake context parallel cache
-            fake_cp = i + 1 < num_seconds
             start_frame, end_frame = (0, 3) if i == 0 else (2 * i + 1, 2 * i + 3)
-            current_frames = vae.decode(latents[:, :, start_frame:end_frame], fake_cp=fake_cp).sample
+            current_frames = vae.decode(latents[:, :, start_frame:end_frame]).sample
             frames.append(current_frames)
-            mm.soft_empty_cache()
+            
+            pbar.update(1)
+        vae.clear_fake_context_parallel_cache()
         vae.to(offload_device)
+        mm.soft_empty_cache()
 
         frames = torch.cat(frames, dim=2)
         video = pipeline["pipe"].video_processor.postprocess_video(video=frames, output_type="pt")
diff --git a/readme.md b/readme.md
index e2f3c01..57b6b9a 100644
--- a/readme.md
+++ b/readme.md
@@ -1,8 +1,6 @@
 # WORK IN PROGRESS
 
-Currently requires diffusers with PR: https://github.com/huggingface/diffusers/pull/9082
-
-This is specified in requirements.txt
+Requires diffusers 0.30.0 (this is specified in requirements.txt)
 
 
 https://github.com/user-attachments/assets/9e41f37b-2bb3-411c-81fa-e91b80da2559
diff --git a/requirements.txt b/requirements.txt
index a3887f2..a4e18bd 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,2 @@
 huggingface_hub
-git+https://github.com/huggingface/diffusers.git@878f609aa5ce4a78fea0f048726889debde1d7e8#egg=diffusers
\ No newline at end of file
+diffusers>=0.30.0
\ No newline at end of file