nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[docs]: classify the Pika H3 Flex pipeline config fields

Browse Source
This commit is contained in:
Aryan Kumar
2026-10-29 18:51:52 -07:00
parent fd9f06654e
commit c36105ae56
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/design/inference_schema_parity_inventory.yaml
+4
View File
@@ -452,6 +452,9 @@ surfaces:
kv_cache_device:
target: generator.pipeline.experimental.kv_cache_device
sources: [fastvideo.configs.pipelines.qwen_image21.QwenImage21PipelineConfig]
pika_resolution_tier:
target: generator.pipeline.experimental.pika_resolution_tier
sources: [fastvideo.configs.pipelines.pika_h3_flex.PikaH3FlexPipelineConfig]
compatibility_only:
batch_size: "Gen3C inference-only tuning field pending typed batching design."
gradient_checkpointing: "Gen3C inference-only compatibility field pending typed batching design."
@@ -465,6 +468,7 @@ surfaces:
frame_receptive_field: "MagiHuman internal data-proxy receptive-field setting."
image_conditioning: "MagiHuman preset variant marker for reference-image conditioning."
pdd_step_indices: "MiniMax-H3 PDD fine-grid partition; resolve_checkpoint_settings sets it from fastvideo_inference.json."
pika_denoising_steps: "Pika H3 Flex six-forward re-noise ladder fixed by the adapter contract; check_pipeline_config rejects any other value."
ref_audio_offset: "MagiHuman internal data-proxy audio alignment offset."
sr_local_attn_layers: "MagiHuman SR internal sparse-attention layer selection."
text_offset: "MagiHuman internal data-proxy text alignment offset."