Instructions to use jadechoghari/VidToMe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jadechoghari/VidToMe with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jadechoghari/VidToMe", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update generate.py
Browse files- generate.py +2 -1
generate.py
CHANGED
|
@@ -355,7 +355,8 @@ class Generator(nn.Module):
|
|
| 355 |
clean_latent = self.ddim_sample(self.init_noise, conds)
|
| 356 |
torch.cuda.empty_cache()
|
| 357 |
clean_frames = self.decode_latents_batch(clean_latent)
|
| 358 |
-
cur_output_path = os.path.join(output_path, edit_name)
|
|
|
|
| 359 |
save_config(self.config, cur_output_path, gene = True)
|
| 360 |
save_video(clean_frames, cur_output_path, save_frame = self.save_frame)
|
| 361 |
|
|
|
|
| 355 |
clean_latent = self.ddim_sample(self.init_noise, conds)
|
| 356 |
torch.cuda.empty_cache()
|
| 357 |
clean_frames = self.decode_latents_batch(clean_latent)
|
| 358 |
+
# cur_output_path = os.path.join(output_path, edit_name)
|
| 359 |
+
cur_output_path = os.path.join("./", edit_name)
|
| 360 |
save_config(self.config, cur_output_path, gene = True)
|
| 361 |
save_video(clean_frames, cur_output_path, save_frame = self.save_frame)
|
| 362 |
|