Instructions to use flashlizard/Sketch3DVE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use flashlizard/Sketch3DVE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("flashlizard/Sketch3DVE", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_class_name": "CogVideoControlNetModel", | |
| "_diffusers_version": "0.30.1", | |
| "_name_or_path": "control-ini-new/viewcrafter_editing_10_blocks/checkpoint-4000", | |
| "activation_fn": "gelu-approximate", | |
| "attention_bias": true, | |
| "attention_head_dim": 64, | |
| "control_block_index": [ | |
| 0, | |
| 3, | |
| 6, | |
| 9, | |
| 12, | |
| 15, | |
| 18, | |
| 21, | |
| 24, | |
| 27 | |
| ], | |
| "dropout": 0.0, | |
| "norm_elementwise_affine": true, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 30, | |
| "time_embed_dim": 512 | |
| } | |