|
Download README.md from someonecantcode/FlowMatching: direct link, hf CLI and curl.
- Browser
- Download file 1.04 kB
-
https://huggingface.co/someonecantcode/FlowMatching/resolve/1dd23639410aefb7f3c8a4ab945ebef4678d4fc2/README.md
- Command line
-
hf download hf://someonecantcode/FlowMatching@1dd23639410aefb7f3c8a4ab945ebef4678d4fc2/README.md
-
curl -L -o README.md https://huggingface.co/someonecantcode/FlowMatching/resolve/1dd23639410aefb7f3c8a4ab945ebef4678d4fc2/README.md
1.04 kB
| Weights for mmDiT and VAE. | |
| Hyperparamters for model used. | |
| ``` | |
| @dataclass | |
| class TrainConfig: | |
| lr: float = 1e-4 | |
| batch_size: int = 8 | |
| total_steps: int = 10000 # 50k steps is ideal. | |
| lr_cooldown_steps: int = 20000 | |
| starting_step: int = 0 | |
| logging_interval: int = 100 | |
| grad_accum_steps: int = 2 # not really needed | |
| save_dir: str = "./saved_models/" | |
| ckpt: str = "flowmatch-ckpt.pt" | |
| @dataclass | |
| class VAEConfig: | |
| kl_beta: float = 5e-2 | |
| fft_weight: float = 0.05 | |
| lpips_weight: float = 0.5 | |
| latent_channels: tuple[int, ...] = (128, 256, 512, 512) | |
| z_channels: int = 32 | |
| n_heads: int = 8 | |
| resnet_blocks: int = 2 | |
| @dataclass | |
| class mmDiTConfig: | |
| d_model: int = 768 | |
| n_heads: int = 32 | |
| n_blocks: int = 16 | |
| patch_size: int = 2 | |
| color_channels: int = 32 # z_channels | |
| height: int = 32 # latent | |
| width: int = 32 # latent | |
| t_channels: int = 64 | |
| ``` | |
| --- | |
| license: gpl-3.0 | |
| datasets: | |
| - stanford-vision-lab/gpic | |
| language: | |
| - en | |
| pipeline_tag: image-text-to-image | |
| tags: | |
| - VAE | |
| - mmDiT | |
| --- |