Will LinandClaude Fable 5
755f4a7967
vae_parallel_decode / vae_parallel_encode / vae_parallel_decode_strategy are model-specific optimization knobs (compatibility_only, like VSA_sparsity). VSA_tile_size came in with the merged tile-64 route without an inventory entry and failed test_fastvideo_args_fields_are_classified on the whole stack; classify it the same way. The remaining pipeline_config inventory gaps (image_encoder_precisions, ...) predate this branch and are left for the owning PRs. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
601 lines
34 KiB
YAML
601 lines
34 KiB
YAML
status_definitions:
|
|
kept: "Public field remains on a public adapter surface with the same meaning."
|
|
moved: "Public field remains supported but normalizes into a different nested path."
|
|
preset_owned: "Public field remains supported only through a model/preset-specific surface."
|
|
compatibility_only: "Legacy public field remains adapter-only during migration and is not part of the canonical typed schema."
|
|
private_only: "Field should only be handled by private adapters and is not a public FastVideo compatibility promise."
|
|
internal_only: "Field is runtime/config plumbing and should not be part of the new public typed inference API."
|
|
|
|
surfaces:
|
|
fastvideo_args:
|
|
moved:
|
|
model_path: generator.model_path
|
|
workload_type: generator.pipeline.workload_type
|
|
distributed_executor_backend: generator.engine.execution_backend
|
|
trust_remote_code: generator.trust_remote_code
|
|
revision: generator.revision
|
|
num_gpus: generator.engine.num_gpus
|
|
tp_size: generator.engine.parallelism.tp_size
|
|
sp_size: generator.engine.parallelism.sp_size
|
|
hsdp_replicate_dim: generator.engine.parallelism.hsdp_replicate_dim
|
|
hsdp_shard_dim: generator.engine.parallelism.hsdp_shard_dim
|
|
dist_timeout: generator.engine.parallelism.dist_timeout
|
|
lora_path: generator.pipeline.components.lora_path
|
|
dit_cpu_offload: generator.engine.offload.dit
|
|
use_fsdp_inference: generator.engine.use_fsdp_inference
|
|
dit_layerwise_offload: generator.engine.offload.dit_layerwise
|
|
text_encoder_cpu_offload: generator.engine.offload.text_encoder
|
|
image_encoder_cpu_offload: generator.engine.offload.image_encoder
|
|
vae_cpu_offload: generator.engine.offload.vae
|
|
pin_cpu_memory: generator.engine.offload.pin_cpu_memory
|
|
enable_torch_compile: generator.engine.compile.enabled
|
|
enable_torch_compile_text_encoder: generator.engine.compile.text_encoder_enabled
|
|
enable_torch_compile_vae: generator.engine.compile.vae_enabled
|
|
enable_torch_compile_audio_vae: generator.engine.compile.audio_vae_enabled
|
|
torch_compile_kwargs: generator.engine.compile.backend,fullgraph,mode,dynamic,extras
|
|
torch_compile_kwargs_dit: generator.engine.compile.dit_kwargs
|
|
torch_compile_kwargs_text_encoder: generator.engine.compile.text_encoder_kwargs
|
|
torch_compile_kwargs_vae: generator.engine.compile.vae_kwargs
|
|
torch_compile_kwargs_audio_vae: generator.engine.compile.audio_vae_kwargs
|
|
transformer_quant: generator.engine.quantization.transformer_quant
|
|
disable_autocast: generator.engine.disable_autocast
|
|
enable_stage_verification: generator.engine.enable_stage_verification
|
|
prompt_txt: request.inputs.prompt_path
|
|
override_text_encoder_safetensors: generator.pipeline.components.text_encoder_weights
|
|
override_text_encoder_quant: generator.engine.quantization.text_encoder_quant
|
|
transformer_quant: generator.engine.quantization.transformer_quant
|
|
override_transformer_cls_name: generator.pipeline.components.override_transformer_cls_name
|
|
init_weights_from_safetensors: generator.pipeline.components.transformer_weights
|
|
init_weights_from_safetensors_2: generator.pipeline.components.transformer_2_weights
|
|
override_pipeline_cls_name: generator.pipeline.components.override_pipeline_cls_name
|
|
boundary_ratio: request.sampling.boundary_ratio
|
|
ltx2_vae_tiling: generator.pipeline.vae_tiling
|
|
refine_enabled: generator.pipeline.preset_overrides.refine.enabled
|
|
refine_upsampler_path: generator.pipeline.components.upsampler_weights
|
|
refine_lora_path: generator.pipeline.components.lora_path
|
|
refine_num_inference_steps: request.stage_overrides.refine.num_inference_steps
|
|
refine_guidance_scale: request.stage_overrides.refine.guidance_scale
|
|
refine_add_noise: generator.pipeline.preset_overrides.refine.add_noise
|
|
ltx2_refine_enabled: generator.pipeline.preset_overrides.refine.enabled
|
|
ltx2_refine_upsampler_path: generator.pipeline.components.upsampler_weights
|
|
ltx2_refine_lora_path: generator.pipeline.components.lora_path
|
|
ltx2_refine_num_inference_steps: request.stage_overrides.refine.num_inference_steps
|
|
ltx2_refine_guidance_scale: request.stage_overrides.refine.guidance_scale
|
|
ltx2_refine_add_noise: generator.pipeline.preset_overrides.refine.add_noise
|
|
preset_owned:
|
|
ltx2_vae_spatial_tile_size_in_pixels: generator.pipeline.preset_overrides.ltx2.vae.spatial_tile_size_in_pixels
|
|
ltx2_vae_spatial_tile_overlap_in_pixels: generator.pipeline.preset_overrides.ltx2.vae.spatial_tile_overlap_in_pixels
|
|
ltx2_vae_temporal_tile_size_in_frames: generator.pipeline.preset_overrides.ltx2.vae.temporal_tile_size_in_frames
|
|
ltx2_vae_temporal_tile_overlap_in_frames: generator.pipeline.preset_overrides.ltx2.vae.temporal_tile_overlap_in_frames
|
|
ltx2_initial_latent_path: request.extensions.ltx2.initial_latent_path
|
|
ltx2_audio_latent_path: request.extensions.ltx2.audio_latent_path
|
|
compatibility_only:
|
|
mode: "Legacy multi-mode FastVideoArgs switch; typed inference config should not expose execution mode."
|
|
inference_mode: "Legacy boolean mirror of mode; kept only through adapters while FastVideoArgs remains."
|
|
lora_nickname: "Legacy adapter-selection surface pending LoRA API cleanup."
|
|
lora_target_modules: "Legacy LoRA configuration surface pending dedicated component API."
|
|
output_type: "Legacy output formatting surface pending GenerationResult cleanup."
|
|
VSA_sparsity: "Model-specific inference optimization not yet represented in the typed public schema."
|
|
VSA_tile_size: "VSA-H3 tile geometry request; model-specific optimization not yet represented in the typed public schema."
|
|
vae_parallel_decode: "MiniMax-H3 sequence-parallel VAE decode opt-in; model-specific optimization not yet represented in the typed public schema."
|
|
vae_parallel_encode: "MiniMax-H3 sequence-parallel reference VAE encode opt-in; model-specific optimization not yet represented in the typed public schema."
|
|
vae_parallel_decode_strategy: "Chunk-transport collective for vae_parallel_decode; model-specific optimization not yet represented in the typed public schema."
|
|
attention_backend: "Process-wide default attention-backend request applied per component at load time; kernel-selection knob not yet represented in the typed public schema."
|
|
moba_config_path: "Model-specific MoBA optimization surface not yet represented in the typed public schema."
|
|
master_port: "Executor/bootstrap compatibility field; not part of the canonical inference schema."
|
|
refine_transformer_path: "Generic stage-2 refine transformer override; no typed equivalent yet."
|
|
refine_noise_path: "Generic stage-2 refine noise override; no typed equivalent yet."
|
|
refine_audio_noise_path: "Generic stage-2 refine audio noise override; no typed equivalent yet."
|
|
ltx2_refine_transformer_path: "LTX-2 refine transformer carrier; no typed equivalent yet."
|
|
ltx2_refine_noise_path: "LTX-2 refine noise carrier; no typed equivalent yet."
|
|
ltx2_refine_audio_noise_path: "LTX-2 refine audio noise carrier; no typed equivalent yet."
|
|
ltx2_legacy_native_noise_order: "LTX-2 SSIM compatibility knob preserving legacy native latent noise ordering."
|
|
ltx2_use_distilled_sigmas: "LTX-2 compatibility knob gating use of distilled sigma schedule."
|
|
private_only:
|
|
ray_placement_group: "Ray deployment-only field."
|
|
ray_runtime_env: "Ray deployment-only field."
|
|
internal_only:
|
|
pipeline_config: "Legacy internal carrier object."
|
|
preprocess_config: "Legacy preprocess carrier object."
|
|
moba_config: "Derived runtime config loaded from moba_config_path."
|
|
model_paths: "Runtime bookkeeping."
|
|
model_loaded: "Runtime bookkeeping."
|
|
|
|
pipeline_config_base:
|
|
moved:
|
|
pipeline_config_path: generator.pipeline.components.pipeline_config_path
|
|
preset_owned:
|
|
embedded_cfg_scale: generator.pipeline.preset_overrides.embedded_cfg_scale
|
|
flow_shift: generator.pipeline.preset_overrides.flow_shift
|
|
flow_shift_sr: generator.pipeline.preset_overrides.flow_shift_sr
|
|
is_causal: generator.pipeline.preset_overrides.is_causal
|
|
vae_tiling: generator.pipeline.preset_overrides.vae_tiling
|
|
vae_sp: generator.pipeline.preset_overrides.vae_sp
|
|
dmd_denoising_steps: generator.pipeline.preset_overrides.dmd_denoising_steps
|
|
ti2v_task: generator.pipeline.preset_overrides.ti2v_task
|
|
lucy_edit_task: generator.pipeline.preset_overrides.lucy_edit_task
|
|
boundary_ratio: generator.pipeline.preset_overrides.boundary_ratio
|
|
compatibility_only:
|
|
model_path: "Redundant with generator.model_path."
|
|
disable_autocast: "Duplicated by generator.engine.disable_autocast during migration."
|
|
dit_precision: "Precision override pending dedicated typed component precision design."
|
|
upsampler_precision: "Precision override pending dedicated typed component precision design."
|
|
vae_precision: "Precision override pending dedicated typed component precision design."
|
|
vae_decode_precision: "Decode-only precision override pending dedicated typed component precision design."
|
|
image_encoder_precision: "Precision override pending dedicated typed component precision design."
|
|
text_encoder_precisions: "Precision override pending dedicated typed component precision design."
|
|
internal_only:
|
|
dit_config: "Legacy internal component config object."
|
|
upsampler_config: "Legacy internal component config object."
|
|
vae_config: "Legacy internal component config object."
|
|
image_encoder_config: "Legacy internal component config object."
|
|
text_encoder_configs: "Legacy internal component config object."
|
|
preprocess_text_funcs: "Internal text preprocessing hooks."
|
|
postprocess_text_funcs: "Internal text postprocessing hooks."
|
|
scheduler_step_in_fp32: "Runtime scheduler precision toggle; not part of the public typed inference API."
|
|
|
|
pipeline_config_extensions:
|
|
preset_owned:
|
|
flux2_text_encoder_type:
|
|
sources:
|
|
- fastvideo.configs.pipelines.flux_2.Flux2PipelineConfig
|
|
- fastvideo.configs.pipelines.flux_2.Flux2KleinPipelineConfig
|
|
text_encoder_out_layers:
|
|
sources:
|
|
- fastvideo.configs.pipelines.flux_2.Flux2PipelineConfig
|
|
- fastvideo.configs.pipelines.flux_2.Flux2KleinPipelineConfig
|
|
conditioning_strategy:
|
|
sources:
|
|
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
max_num_conditional_frames:
|
|
sources:
|
|
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
min_num_conditional_frames:
|
|
sources:
|
|
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
sigma_conditional:
|
|
sources:
|
|
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
sigma_data:
|
|
sources:
|
|
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
state_ch:
|
|
sources:
|
|
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
state_t:
|
|
sources:
|
|
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
text_encoder_class:
|
|
sources:
|
|
- fastvideo.configs.pipelines.cosmos.CosmosConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
autoregressive_chunk_frames:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
autoregressive_overlap_frames:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
cfg_behavior:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
color_correction_strength:
|
|
sources:
|
|
- fastvideo.configs.pipelines.dreamx_world.DreamXWorld5BARPipelineConfig
|
|
default_camera_rotation:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
default_movement_distance:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
default_negative_prompt:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
default_trajectory_type:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
filter_points_threshold:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
fps:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
frame_buffer_max:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
moge_model_name:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
noise_aug_strength:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
num_frames:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
offload_moge_after_depth:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
use_moge_depth:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
video_resolution:
|
|
sources:
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CConfig
|
|
- fastvideo.configs.pipelines.gen3c.Gen3CInferenceConfig
|
|
text_encoder_crop_start:
|
|
sources:
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15I2V480PStepDistilledConfig
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15I2V720PConfig
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15SR1080PConfig
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15T2V480PConfig
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15T2V720PConfig
|
|
- fastvideo.configs.pipelines.hyworld.HYWorldConfig
|
|
- fastvideo.configs.pipelines.hyworld.Hunyuan15T2V480PConfig
|
|
text_encoder_max_lengths:
|
|
sources:
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15I2V480PStepDistilledConfig
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15I2V720PConfig
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15SR1080PConfig
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15T2V480PConfig
|
|
- fastvideo.configs.pipelines.hunyuan15.Hunyuan15T2V720PConfig
|
|
- fastvideo.configs.pipelines.hyworld.HYWorldConfig
|
|
- fastvideo.configs.pipelines.hyworld.Hunyuan15T2V480PConfig
|
|
precision:
|
|
sources:
|
|
- fastvideo.configs.pipelines.lingbotworld.LingBotWorldI2V480PConfig
|
|
- fastvideo.configs.pipelines.lingbotworld.Wan2_2_I2V_A14B_Config
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionI2VConfig
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionI2V_A14B_Config
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2VConfig
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2V_14B_Config
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2V_1_3B_Config
|
|
- fastvideo.configs.pipelines.wan.FastWan2_1_T2V_480P_Config
|
|
- fastvideo.configs.pipelines.wan.FastWan2_2_TI2V_5B_Config
|
|
- fastvideo.configs.pipelines.matrixgame2.MatrixGame2BaseI2V480PConfig
|
|
- fastvideo.configs.pipelines.matrixgame2.MatrixGame2I2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.SelfForcingWan2_2_T2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.SelfForcingWanT2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.WANV2VConfig
|
|
- fastvideo.configs.pipelines.wan.Wan2_2_I2V_A14B_Config
|
|
- fastvideo.configs.pipelines.wan.Wan2_2_T2V_A14B_Config
|
|
- fastvideo.configs.pipelines.wan.Wan2_2_TI2V_5B_Config
|
|
- fastvideo.configs.pipelines.wan.WanI2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.WanI2V720PConfig
|
|
- fastvideo.configs.pipelines.wan.WanT2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.WanT2V720PConfig
|
|
warp_denoising_step:
|
|
sources:
|
|
- fastvideo.configs.pipelines.lingbotworld.LingBotWorldI2V480PConfig
|
|
- fastvideo.configs.pipelines.lingbotworld.Wan2_2_I2V_A14B_Config
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionI2VConfig
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionI2V_A14B_Config
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2VConfig
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2V_14B_Config
|
|
- fastvideo.configs.pipelines.turbodiffusion.TurboDiffusionT2V_1_3B_Config
|
|
- fastvideo.configs.pipelines.wan.FastWan2_1_T2V_480P_Config
|
|
- fastvideo.configs.pipelines.wan.FastWan2_2_TI2V_5B_Config
|
|
- fastvideo.configs.pipelines.matrixgame2.MatrixGame2BaseI2V480PConfig
|
|
- fastvideo.configs.pipelines.matrixgame2.MatrixGame2I2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.SelfForcingWan2_2_T2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.SelfForcingWanT2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.WANV2VConfig
|
|
- fastvideo.configs.pipelines.wan.Wan2_2_I2V_A14B_Config
|
|
- fastvideo.configs.pipelines.wan.Wan2_2_T2V_A14B_Config
|
|
- fastvideo.configs.pipelines.wan.Wan2_2_TI2V_5B_Config
|
|
- fastvideo.configs.pipelines.wan.WanI2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.WanI2V720PConfig
|
|
- fastvideo.configs.pipelines.wan.WanT2V480PConfig
|
|
- fastvideo.configs.pipelines.wan.WanT2V720PConfig
|
|
bsa_cdf_threshold:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
bsa_chunk_k:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
bsa_chunk_q:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
bsa_params:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
bsa_sparsity:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
enable_bsa:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
enable_kv_cache:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
enhance_hf:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
offload_kv_cache:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
t_thresh:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
use_distill:
|
|
sources: [fastvideo.configs.pipelines.longcat.LongCatT2V480PConfig, fastvideo.configs.pipelines.longcat.LongCatT2V704PConfig]
|
|
scheduler_arch:
|
|
sources:
|
|
- fastvideo.configs.pipelines.sd35.SD35Config
|
|
- fastvideo.configs.pipelines.zimage.ZImagePipelineConfig
|
|
text_encoder_archs:
|
|
sources:
|
|
- fastvideo.configs.pipelines.sd35.SD35Config
|
|
- fastvideo.configs.pipelines.zimage.ZImagePipelineConfig
|
|
tokenizer_archs:
|
|
sources:
|
|
- fastvideo.configs.pipelines.sd35.SD35Config
|
|
- fastvideo.configs.pipelines.zimage.ZImagePipelineConfig
|
|
transformer_arch:
|
|
sources:
|
|
- fastvideo.configs.pipelines.sd35.SD35Config
|
|
- fastvideo.configs.pipelines.zimage.ZImagePipelineConfig
|
|
vae_arch:
|
|
sources:
|
|
- fastvideo.configs.pipelines.sd35.SD35Config
|
|
- fastvideo.configs.pipelines.zimage.ZImagePipelineConfig
|
|
expand_timesteps:
|
|
sources:
|
|
- fastvideo.configs.pipelines.wan.FastWan2_2_TI2V_5B_Config
|
|
- fastvideo.configs.pipelines.wan.Wan2_2_TI2V_5B_Config
|
|
context_noise:
|
|
sources: [fastvideo.configs.pipelines.matrixgame2.MatrixGame2I2V480PConfig]
|
|
num_frames_per_block:
|
|
sources: [fastvideo.configs.pipelines.matrixgame2.MatrixGame2I2V480PConfig]
|
|
audio_channels:
|
|
sources:
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
|
|
audio_end_in_s:
|
|
sources:
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
|
|
audio_start_in_s:
|
|
sources:
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
|
|
max_audio_duration_s:
|
|
sources:
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
|
|
sample_size:
|
|
sources:
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
|
|
sampling_rate:
|
|
sources:
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioT2AConfig
|
|
- fastvideo.configs.pipelines.stable_audio.StableAudioOpenSmallConfig
|
|
audio_txt_guidance_scale:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanBaseConfig]
|
|
cfg_number:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanBaseConfig]
|
|
cfg_trick_start_frame:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig]
|
|
cfg_trick_value:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig]
|
|
noise_value:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig]
|
|
sr_audio_noise_scale:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig]
|
|
sr_height:
|
|
sources:
|
|
- fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig
|
|
- fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR1080pConfig
|
|
sr_num_inference_steps:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig]
|
|
sr_video_txt_guidance_scale:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig]
|
|
sr_width:
|
|
sources:
|
|
- fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig
|
|
- fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR1080pConfig
|
|
t5_gemma_target_length:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanBaseConfig]
|
|
use_cfg_trick:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanSR540pConfig]
|
|
video_guidance_high_t_threshold:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanBaseConfig]
|
|
video_guidance_low_t_value:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanBaseConfig]
|
|
video_txt_guidance_scale:
|
|
sources: [fastvideo.pipelines.basic.magi_human.pipeline_configs.MagiHumanBaseConfig]
|
|
compatibility_only:
|
|
batch_size: "Gen3C inference-only tuning field pending typed batching design."
|
|
gradient_checkpointing: "Gen3C inference-only compatibility field pending typed batching design."
|
|
guidance_scale: "Gen3C pipeline-level default pending preset/default-request cleanup."
|
|
num_inference_steps: "Gen3C pipeline-level default pending preset/default-request cleanup."
|
|
internal_only:
|
|
audio_decoder_config: "Legacy internal component config object."
|
|
audio_decoder_precision: "Precision override pending dedicated component precision design."
|
|
audio_vae_config: "MagiHuman internal audio VAE component config object."
|
|
coords_style: "MagiHuman internal data-proxy coordinate convention."
|
|
frame_receptive_field: "MagiHuman internal data-proxy receptive-field setting."
|
|
image_conditioning: "MagiHuman preset variant marker for reference-image conditioning."
|
|
ref_audio_offset: "MagiHuman internal data-proxy audio alignment offset."
|
|
scheduler_sigma_min: "Z-Image scheduler parity invariant; not part of the public typed inference API."
|
|
scheduler_use_reference_discrete_timesteps: "Z-Image scheduler parity invariant; not part of the public typed inference API."
|
|
sr_local_attn_layers: "MagiHuman SR internal sparse-attention layer selection."
|
|
text_offset: "MagiHuman internal data-proxy text alignment offset."
|
|
vae_stride: "MagiHuman internal VAE/data-proxy stride setting."
|
|
z_dim: "MagiHuman internal VAE latent channel setting."
|
|
vocoder_config: "Legacy internal component config object."
|
|
vocoder_precision: "Precision override pending dedicated component precision design."
|
|
|
|
sampling_param_base:
|
|
moved:
|
|
image_path: request.inputs.image_path
|
|
pil_image: request.inputs.pil_image
|
|
last_image: request.inputs.last_image
|
|
references: request.inputs.references
|
|
video_path: request.inputs.video_path
|
|
latents: request.inputs.latents
|
|
audio_latents: request.inputs.audio_latents
|
|
mouse_cond: request.inputs.mouse_cond
|
|
keyboard_cond: request.inputs.keyboard_cond
|
|
grid_sizes: request.inputs.grid_sizes
|
|
pose: request.inputs.pose
|
|
c2ws_plucker_emb: request.inputs.c2ws_plucker_emb
|
|
action_path: request.inputs.action_path
|
|
refine_from: request.inputs.refine_from
|
|
stage1_video: request.inputs.stage1_video
|
|
prompt: request.prompt
|
|
negative_prompt: request.negative_prompt
|
|
prompt_path: request.inputs.prompt_path
|
|
output_path: request.output.output_path
|
|
output_video_name: request.output.output_video_name
|
|
num_videos_per_prompt: request.sampling.num_videos_per_prompt
|
|
seed: request.sampling.seed
|
|
max_sequence_length: request.sampling.max_sequence_length
|
|
num_frames: request.sampling.num_frames
|
|
height: request.sampling.height
|
|
width: request.sampling.width
|
|
height_sr: request.sampling.height_sr
|
|
width_sr: request.sampling.width_sr
|
|
fps: request.sampling.fps
|
|
num_inference_steps: request.sampling.num_inference_steps
|
|
num_inference_steps_sr: request.sampling.num_inference_steps_sr
|
|
guidance_scale: request.sampling.guidance_scale
|
|
batch_cfg: request.sampling.batch_cfg
|
|
guidance_scale_2: request.sampling.guidance_scale_2
|
|
cfg_normalization: request.sampling.cfg_normalization
|
|
cfg_truncation: request.sampling.cfg_truncation
|
|
guidance_rescale: request.sampling.guidance_rescale
|
|
use_embedded_guidance: request.sampling.use_embedded_guidance
|
|
true_cfg_scale: request.sampling.true_cfg_scale
|
|
boundary_ratio: request.sampling.boundary_ratio
|
|
sigmas: request.sampling.sigmas
|
|
enable_teacache: request.runtime.enable_teacache
|
|
save_video: request.output.save_video
|
|
return_frames: request.output.return_frames
|
|
return_trajectory_latents: request.runtime.return_trajectory_latents
|
|
return_trajectory_decoded: request.runtime.return_trajectory_decoded
|
|
continuation_state: request.state
|
|
return_continuation_state: request.output.return_state
|
|
preset_owned:
|
|
t_thresh: request.stage_overrides.refine.t_thresh
|
|
spatial_refine_only: request.stage_overrides.refine.spatial_refine_only
|
|
num_cond_frames: request.stage_overrides.refine.num_cond_frames
|
|
trajectory_type: request.extensions.gen3c.trajectory_type
|
|
movement_distance: request.extensions.gen3c.movement_distance
|
|
camera_rotation: request.extensions.gen3c.camera_rotation
|
|
prompt_attention_mask: request.extensions.hyworld.prompt_attention_mask
|
|
negative_attention_mask: request.extensions.hyworld.negative_attention_mask
|
|
camera_states: request.extensions.hunyuangamecraft.camera_states
|
|
camera_trajectory: request.extensions.hunyuangamecraft.camera_trajectory
|
|
action_list: request.extensions.hunyuangamecraft.action_list
|
|
action_speed_list: request.extensions.hunyuangamecraft.action_speed_list
|
|
gt_latents: request.extensions.hunyuangamecraft.gt_latents
|
|
conditioning_mask: request.extensions.hunyuangamecraft.conditioning_mask
|
|
ltx2_cfg_scale_video: request.extensions.ltx2.cfg_scale_video
|
|
ltx2_cfg_scale_audio: request.extensions.ltx2.cfg_scale_audio
|
|
ltx2_modality_scale_video: request.extensions.ltx2.modality_scale_video
|
|
ltx2_modality_scale_audio: request.extensions.ltx2.modality_scale_audio
|
|
ltx2_rescale_scale: request.extensions.ltx2.rescale_scale
|
|
ltx2_stg_scale_video: request.extensions.ltx2.stg_scale_video
|
|
ltx2_stg_scale_audio: request.extensions.ltx2.stg_scale_audio
|
|
ltx2_stg_blocks_video: request.extensions.ltx2.stg_blocks_video
|
|
ltx2_stg_blocks_audio: request.extensions.ltx2.stg_blocks_audio
|
|
ltx2_images: request.extensions.ltx2.images
|
|
ltx2_image_crf: request.stage_overrides.refine.image_crf
|
|
ltx2_conditioning_latent_stage1: request.extensions.ltx2.conditioning_latent_stage1
|
|
ltx2_conditioning_latent_stage2: request.extensions.ltx2.conditioning_latent_stage2
|
|
ltx2_video_conditions: request.extensions.ltx2.video_conditions
|
|
audio_start_in_s: request.extensions.stable_audio.audio_start_in_s
|
|
audio_end_in_s: request.extensions.stable_audio.audio_end_in_s
|
|
init_audio: request.extensions.stable_audio.init_audio
|
|
init_audio_strength: request.extensions.stable_audio.init_audio_strength
|
|
init_noise_level: request.extensions.stable_audio.init_noise_level
|
|
inpaint_audio: request.extensions.stable_audio.inpaint_audio
|
|
inpaint_mask: request.extensions.stable_audio.inpaint_mask
|
|
internal_only:
|
|
data_type: "Derived from the request shape and not a public input."
|
|
|
|
sampling_param_extensions: {}
|
|
|
|
openai_image_request:
|
|
kept:
|
|
model: "HTTP adapter model-routing field."
|
|
response_format: "HTTP adapter response formatting field."
|
|
output_format: "HTTP adapter output-format field."
|
|
background: "HTTP adapter output-format field."
|
|
quality: "Compatibility field currently accepted by the adapter."
|
|
style: "Compatibility field currently accepted by the adapter."
|
|
user: "Compatibility field currently accepted by the adapter."
|
|
moved:
|
|
prompt: request.prompt
|
|
n: request.sampling.num_videos_per_prompt
|
|
size:
|
|
target: request.sampling.width,height
|
|
note: "Adapter parses OpenAI size strings as WIDTHxHEIGHT and forwards width then height."
|
|
num_inference_steps: request.sampling.num_inference_steps
|
|
guidance_scale: request.sampling.guidance_scale
|
|
true_cfg_scale: request.sampling.true_cfg_scale
|
|
seed: request.sampling.seed
|
|
negative_prompt: request.negative_prompt
|
|
enable_teacache: request.runtime.enable_teacache
|
|
|
|
openai_video_request:
|
|
kept:
|
|
model: "HTTP adapter model-routing field."
|
|
moved:
|
|
prompt: request.prompt
|
|
input_reference: request.inputs.image_path
|
|
reference_url: request.inputs.image_path
|
|
size:
|
|
target: request.sampling.width,height
|
|
note: "Adapter parses OpenAI size strings as WIDTHxHEIGHT and forwards width then height."
|
|
fps: request.sampling.fps
|
|
num_frames: request.sampling.num_frames
|
|
seed: request.sampling.seed
|
|
num_inference_steps: request.sampling.num_inference_steps
|
|
guidance_scale: request.sampling.guidance_scale
|
|
guidance_scale_2: request.sampling.guidance_scale_2
|
|
true_cfg_scale: request.sampling.true_cfg_scale
|
|
negative_prompt: request.negative_prompt
|
|
enable_teacache: request.runtime.enable_teacache
|
|
output_path: request.output.output_path
|
|
compatibility_only:
|
|
seconds:
|
|
target: request.sampling.num_frames
|
|
note: "HTTP adapter duration convenience field. If num_frames is omitted, the adapter computes num_frames = fps * seconds."
|
|
|
|
cli:
|
|
notes:
|
|
- "CLI parity is checked against the actual generate/serve parser dest sets."
|
|
- "The inventory tracks parser dest names, excluding argparse's implicit help action."
|
|
- "The refactored inference CLI is config-only: subcommands expose only --config, and any additional CLI input must use dotted override paths."
|
|
generate:
|
|
explicit_local_fields:
|
|
- config
|
|
expected_dests:
|
|
- config
|
|
serve:
|
|
explicit_local_fields:
|
|
- config
|
|
expected_dests:
|
|
- config
|