CFSynthesis: Controllable and Free-view 3D Human Video Synthesis
Paper • 2412.11067 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("lycui/CFSynthesis", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Model Sources
- Repository: zju3dv/CFSynthesis
- Paper: https://arxiv.org/abs/2412.11067
Directory Structure
./PROJECT_ROOT/
|-- ckpts
| |-- denoising_unet.pth
| |-- guidance_encoder_depth.pth
| |-- guidance_encoder_dwpose.pth
| |-- guidance_encoder_normal.pth
| |-- guidance_encoder_semantic_map.pth
| |-- reference_unet.pth
|-- control_v11p_sd15_openpose
| |-- diffusion_pytorch_model.bin
|-- image_encoder
| |-- config.json
| `-- pytorch_model.bin
|-- sd-vae-ft-mse
| |-- config.json
| |-- diffusion_pytorch_model.bin
| `-- diffusion_pytorch_model.safetensors
`-- stable-diffusion-v1-5
|-- feature_extractor
| `-- preprocessor_config.json
|-- model_index.json
|-- unet
| |-- config.json
| `-- diffusion_pytorch_model.bin
`-- v1-inference.yaml
Reference
Thanks to the following projects and authors:
- [1] runwayml. Stable Diffusion v1-5.
- [2] stabilityai. sd-vae-ft-mse
- [3] bdsqlsz. image_encoder
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support