Create config.yaml

config.yaml

@@ -0,0 +1,52 @@
+conditions: [lineart, edge, depth, normal, albedo, segmentation, openpose]
+# model config
+model:
+  model: Jodi_1600M_P1_D20
+  image_size: 1024
+  mixed_precision: bf16
+  fp32_attention: true
+  load_from:
+  resume_from:
+  pe_interpolation: 1.
+  attn_type: linear
+  mlp_acts:
+    - silu
+    - silu
+    -
+  mlp_ratio: 2.5
+  use_pe: true
+  qk_norm: false
+  class_dropout_prob: 0.1
+# VAE setting
+vae:
+  vae_type: dc-ae
+  vae_pretrained: mit-han-lab/dc-ae-f32c32-sana-1.0
+  scale_factor: 0.41407
+  vae_latent_dim: 32
+  vae_downsample_rate: 32
+  sample_posterior: true
+# text encoder
+text_encoder:
+  text_encoder_name: gemma-2-2b-it
+  y_norm: true
+  y_norm_scale_factor: 0.01
+  model_max_length: 300
+  # CHI
+  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: '
+# Sana schedule Flow
+scheduler:
+  predict_v: true
+  noise_schedule: linear_flow
+  flow_shift: 3.0
+  # logit-normal timestep
+  weighting_scheme: logit_normal
+  logit_mean: 0.0
+  logit_std: 1.0