Skip to content
Python

AccVideo support

DeepBeepMeepdb25325930f7
diff --git a/wan/text2video.py b/wan/text2video.py
index af699b7..3d3d404 100644
--- a/wan/text2video.py
+++ b/wan/text2video.py
@@ -470,14 +470,14 @@ class WanT2V:
latent_noise_factor = t / 1000
for zz, zz_r, ll in zip(z, z_reactive, [latents]):
pass
- # zz[0:16, ref_images_count:overlapped_latents_size + ref_images_count] = zz_r[:, ref_images_count:] * (1.0 - overlap_noise_factor) + torch.randn_like(zz_r[:, ref_images_count:] ) * overlap_noise_factor
- # ll[:, 0:overlapped_latents_size + ref_images_count] = zz_r * (1.0 - latent_noise_factor) + torch.randn_like(zz_r ) * latent_noise_factor
+ zz[0:16, ref_images_count:overlapped_latents_size + ref_images_count] = zz_r[:, ref_images_count:] * (1.0 - overlap_noise_factor) + torch.randn_like(zz_r[:, ref_images_count:] ) * overlap_noise_factor
+ ll[:, 0:overlapped_latents_size + ref_images_count] = zz_r * (1.0 - latent_noise_factor) + torch.randn_like(zz_r ) * latent_noise_factor
if conditioning_latents_size > 0 and overlap_noise > 0:
pass
overlap_noise_factor = overlap_noise / 1000
- latents[:, conditioning_latents_size + ref_images_count:] = latents[:, conditioning_latents_size + ref_images_count:] * (1.0 - overlap_noise_factor) + torch.randn_like(latents[:, conditioning_latents_size + ref_images_count:]) * overlap_noise_factor
- #timestep = [torch.tensor([t.item()] * (conditioning_latents_size + ref_images_count) + [t.item() - overlap_noise]*(len(timesteps) - conditioning_latents_size - ref_images_count))]
+ # latents[:, conditioning_latents_size + ref_images_count:] = latents[:, conditioning_latents_size + ref_images_count:] * (1.0 - overlap_noise_factor) + torch.randn_like(latents[:, conditioning_latents_size + ref_images_count:]) * overlap_noise_factor
+ # timestep = [torch.tensor([t.item()] * (conditioning_latents_size + ref_images_count) + [t.item() - overlap_noise]*(target_shape[1] - conditioning_latents_size - ref_images_count))]
if target_camera != None:
latent_model_input = torch.cat([latents, source_latents], dim=1)
diff --git a/wgp.py b/wgp.py
index b5ba519..5679a68 100644
--- a/wgp.py
+++ b/wgp.py
@@ -42,8 +42,8 @@ global_queue_ref = []
AUTOSAVE_FILENAME = "queue.zip"
PROMPT_VARS_MAX = 10
-target_mmgp_version = "3.4.7"
-WanGP_version = "5.4"
+target_mmgp_version = "3.4.8"
+WanGP_version = "5.41"
prompt_enhancer_image_caption_model, prompt_enhancer_image_caption_processor, prompt_enhancer_llm_model, prompt_enhancer_llm_tokenizer = None, None, None, None
from importlib.metadata import version
@@ -3263,11 +3263,13 @@ def generate_video(
if exp > 0:
from rife.inference import temporal_interpolation
if sliding_window and window_no > 1:
- sample = torch.cat([frames_already_processed[:, -2:-1], sample], dim=1)
+ sample = torch.cat([previous_before_last_frame, sample], dim=1)
+ previous_before_last_frame = sample[:, -2:-1].clone()
sample = temporal_interpolation( os.path.join("ckpts", "flownet.pkl"), sample, exp, device=processing_device)
sample = sample[:, 1:]
else:
sample = temporal_interpolation( os.path.join("ckpts", "flownet.pkl"), sample, exp, device=processing_device)
+ previous_before_last_frame = sample[:, -2:-1].clone()
output_fps = output_fps * 2**exp
@@ -4843,8 +4845,8 @@ def generate_video_tab(update_form = False, state_dict = None, ui_defaults = Non
temporal_upsampling = gr.Dropdown(
choices=[
("Disabled", ""),
- ("Rife x2 (32 frames/s)", "rife2"),
- ("Rife x4 (64 frames/s)", "rife4"),
+ ("Rife x2 frames/s", "rife2"),
+ ("Rife x4 frames/s", "rife4"),
],
value=ui_defaults.get("temporal_upsampling", ""),
visible=True,