Upload config.yaml with huggingface_hub

config.yaml

@@ -0,0 +1,69 @@
+model:
+  model: SanaMSVideoCamCtrl_1600M_P1_D20
+  image_size: 720
+  aspect_ratio_type: ASPECT_RATIO_VIDEO_720_MS_DIV32
+  mixed_precision: bf16
+  fp32_attention: true
+  multi_scale: true
+  camctrl_type: BidirectionalGDNUCPESinglePathLiteLABothTriton
+  attn_type: BidirectionalGDNTriton
+  softmax_every_n: 4
+  linear_head_dim: 112
+  conv_kernel_size: 4
+  k_conv_only: true
+  ffn_type: GLUMBConvTemp
+  t_kernel_size: 3
+  mlp_acts:
+    - silu
+    - silu
+    -
+  mlp_ratio: 3
+  use_pe: true
+  pos_embed_type: wan_rope
+  qk_norm: true
+  cross_norm: true
+  class_dropout_prob: 0.0
+  chunk_split_strategy: first_chunk_plus_one
+  cam_attn_compress: 1
+  init_cam_from_base: true
+  use_chunk_plucker_post_attn: true
+  chunk_plucker_channels: 48
+  chunk_plucker_post_attn_blocks: 20
+
+vae:
+  vae_type: LTX2VAE_diffusers
+  # AutoencoderKLLTX2Video.from_pretrained(<root>, subfolder="vae") expects
+  # a parent directory containing a ``vae/`` diffusers folder. The public
+  # release repo hosts that ``vae/`` folder at its root.
+  vae_pretrained: hf://Efficient-Large-Model/SANA-WM_bidirectional
+  weight_dtype: bfloat16
+  vae_latent_dim: 128
+  vae_downsample_rate: 32
+  vae_stride: [8, 32, 32]
+  use_framewise_encoding: true
+  use_framewise_decoding: true
+  tile_sample_stride_num_frames: 64
+  tile_sample_min_num_frames: 96
+
+text_encoder:
+  text_encoder_name: gemma-2-2b-it
+  y_norm: true
+  y_norm_scale_factor: 0.01
+  model_max_length: 300
+  chi_prompt:
+    - 'Given a user prompt, generate an "Enhanced prompt" that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:'
+    - '- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.'
+    - '- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.'
+    - 'Here are examples of how to transform or refine prompts:'
+    - '- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.'
+    - '- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.'
+    - 'Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:'
+    - 'User Prompt: '
+
+scheduler:
+  predict_flow_v: true
+  noise_schedule: linear_flow
+  pred_sigma: false
+  flow_shift: 9.95
+  inference_flow_shift: 9.8
+  vis_sampler: flow_dpm-solver