JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2025-06-10 17:09:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

update the req

Browse Source
This commit is contained in:
zR 2024-08-29 20:24:23 +08:00
parent 29642ade50
commit b0b029d0fd
3 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -271,7 +271,6 @@ pipe.vae.enable_tiling()
increases by about 10%. Only the `diffusers` version of the model supports quantization. increases by about 10%. Only the `diffusers` version of the model supports quantization.
+ The model only supports English input; other languages can be translated into English during refinement by a large + The model only supports English input; other languages can be translated into English during refinement by a large
model. model.
+
## Friendly Links ## Friendly Links

10
inference/gradio_composite_demo/rife_model.py
View File

@ -42,10 +42,10 @@ def ssim_interpolation_rife(model, samples, exp=1, upscale_amount=1, output_devi
output = [] output = []
# [f, c, h, w] # [f, c, h, w]
for b in range(samples.shape[0]): for b in range(samples.shape[0]):
frame = samples[b: b + 1] frame = samples[b : b + 1]
_, _, h, w = frame.shape _, _, h, w = frame.shape
I0 = samples[b: b + 1] I0 = samples[b : b + 1]
I1 = samples[b + 1: b + 2] if b + 2 < samples.shape[0] else samples[-1:] I1 = samples[b + 1 : b + 2] if b + 2 < samples.shape[0] else samples[-1:]
I0 = pad_image(I0, upscale_amount).to(torch.float) I0 = pad_image(I0, upscale_amount).to(torch.float)
I1 = pad_image(I1, upscale_amount).to(torch.float) I1 = pad_image(I1, upscale_amount).to(torch.float)
# [c, h, w] # [c, h, w]
@ -66,11 +66,11 @@ def ssim_interpolation_rife(model, samples, exp=1, upscale_amount=1, output_devi
tmp_output = [] tmp_output = []
if ssim < 0.2: if ssim < 0.2:
for i in range((2 ** exp) - 1): for i in range((2**exp) - 1):
tmp_output.append(I0) tmp_output.append(I0)
else: else:
tmp_output = make_inference(model, I0, I1, upscale_amount, 2 ** exp - 1) if exp else [] tmp_output = make_inference(model, I0, I1, upscale_amount, 2**exp - 1) if exp else []
frame = pad_image(frame, upscale_amount) frame = pad_image(frame, upscale_amount)
tmp_output = [frame] + tmp_output tmp_output = [frame] + tmp_output

4
requirements.txt
View File

@ -1,5 +1,5 @@
diffusers>=0.30.1 #git+https://github.com/huggingface/diffusers.git@main#egg=diffusers is suggested diffusers>=0.30.1 #git+https://github.com/huggingface/diffusers.git@main#egg=diffusers is suggested
transformers>=4.44.0 # The development team is working on version 0.44.2 transformers>=4.44.2 # The development team is working on version 4.44.2
accelerate>=0.33.0 #git+https://github.com/huggingface/accelerate.git@main#egg=accelerate is suggested accelerate>=0.33.0 #git+https://github.com/huggingface/accelerate.git@main#egg=accelerate is suggested
sentencepiece>=0.2.0 # T5 used sentencepiece>=0.2.0 # T5 used
SwissArmyTransformer>=0.4.12 SwissArmyTransformer>=0.4.12
@ -7,7 +7,7 @@ numpy==1.26.0
torch>=2.4.0 # Tested in 2.2 2.3 2.4 and 2.5, The development team is working on version 2.4.0. torch>=2.4.0 # Tested in 2.2 2.3 2.4 and 2.5, The development team is working on version 2.4.0.
torchvision>=0.19.0 # The development team is working on version 0.19.0. torchvision>=0.19.0 # The development team is working on version 0.19.0.
gradio>=4.42.0 # For HF gradio demo gradio>=4.42.0 # For HF gradio demo
streamlit>=1.37.1 # For streamlit web demo streamlit>=1.38.0 # For streamlit web demo
imageio==2.34.2 # For diffusers inference export video imageio==2.34.2 # For diffusers inference export video
imageio-ffmpeg==0.5.1 # For diffusers inference export video imageio-ffmpeg==0.5.1 # For diffusers inference export video
openai>=1.42.0 # For prompt refiner openai>=1.42.0 # For prompt refiner