configs/ltxv-13b-0.9.8-distilled-fp8.yaml

pipeline_type: multi-scale
checkpoint_path: "ltxv-13b-0.9.8-distilled-fp8.safetensors"
downscale_factor: 0.6666666
spatial_upscaler_model_path: "ltxv-spatial-upscaler-0.9.8.safetensors"
stg_mode: "attention_values" # options: "attention_values", "attention_skip", "residual", "transformer_block"
decode_timestep: 0.05
decode_noise_scale: 0.025
text_encoder_model_name_or_path: "PixArt-alpha/PixArt-XL-2-1024-MS"
precision: "float8_e4m3fn" # options: "float8_e4m3fn", "bfloat16", "mixed_precision"
sampler: "from_checkpoint" # options: "uniform", "linear-quadratic", "from_checkpoint"
prompt_enhancement_words_threshold: 120
prompt_enhancer_image_caption_model_name_or_path: "MiaoshouAI/Florence-2-large-PromptGen-v2.0"
prompt_enhancer_llm_model_name_or_path: "unsloth/Llama-3.2-3B-Instruct"
stochastic_sampling: false

first_pass:
  timesteps: [1.0000, 0.9937, 0.9875, 0.9812, 0.9750, 0.9094, 0.7250]
  guidance_scale: 1
  stg_scale: 0
  rescaling_scale: 1
  skip_block_list: [42]

second_pass:
  timesteps: [0.9094, 0.7250, 0.4219]
  guidance_scale: 1
  stg_scale: 0
  rescaling_scale: 1
  skip_block_list: [42]
  tone_map_compression_ratio: 0.6