171 lines
10 KiB
JSON
171 lines
10 KiB
JSON
{
|
|
"source": {
|
|
"fastvideoCommit": "a2bfc7cdb2a1de2b138258412e42d183444ffe09",
|
|
"description": "Defaults transcribed from FastVideo's registered inference presets, pipeline configs, maintained examples, and support matrix at this commit.",
|
|
"paths": [
|
|
"fastvideo/registry.py",
|
|
"fastvideo/pipelines/basic/*/presets.py",
|
|
"fastvideo/configs/pipelines/*.py",
|
|
"examples/inference/basic/*.py",
|
|
"docs/inference/support_matrix.md"
|
|
]
|
|
},
|
|
"defaults": {
|
|
"model_id": "FastVideo/FastWan2.1-T2V-1.3B-Diffusers",
|
|
"workload_type": "t2v",
|
|
"num_gpus": 1,
|
|
"seed": 1024,
|
|
"dit_cpu_offload": false,
|
|
"dit_layerwise_offload": false,
|
|
"vae_cpu_offload": false,
|
|
"text_encoder_cpu_offload": true,
|
|
"image_encoder_cpu_offload": false,
|
|
"pin_cpu_memory": true,
|
|
"use_fsdp_inference": false
|
|
},
|
|
"workloads": [
|
|
{ "id": "t2v", "name": "Text to Video", "icon": "Film" },
|
|
{ "id": "i2v", "name": "Image to Video", "icon": "Sparkles" },
|
|
{ "id": "ti2v", "name": "Text + Image to Video", "icon": "Layers" },
|
|
{ "id": "game", "name": "Game", "icon": "Zap" }
|
|
],
|
|
"attentionBackends": [
|
|
{ "id": "FLASH_ATTN", "name": "Flash Attention", "shortName": "Flash", "desc": "Default dense attention backend." },
|
|
{ "id": "VIDEO_SPARSE_ATTN", "name": "Video Sparse Attention", "shortName": "VSA", "desc": "Use only with models marked VSA-compatible." },
|
|
{ "id": "SAGE_ATTN", "name": "Sage Attention", "shortName": "SAGE", "desc": "Quantized attention for models marked Sage-compatible." },
|
|
{ "id": "SLA_ATTN", "name": "Sparse-Linear Attention", "shortName": "SLA", "desc": "Required by TurboDiffusion checkpoints." }
|
|
],
|
|
"models": [
|
|
{
|
|
"id": "FastVideo/FastWan2.1-T2V-1.3B-Diffusers",
|
|
"name": "FastWan2.1 T2V",
|
|
"size": "1.3B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 448, "width": 832, "numFrames": 61, "fps": 16, "numInferenceSteps": 3, "guidanceScale": 3, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 8, "boundaryRatio": null, "dmdDenoisingSteps": [1000, 757, 522], "attentionBackends": ["VIDEO_SPARSE_ATTN", "FLASH_ATTN"], "defaultAttentionBackend": "VIDEO_SPARSE_ATTN", "vsaSparsity": 0.8 }
|
|
},
|
|
{
|
|
"id": "FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers",
|
|
"name": "FastWan2.2 TI2V FullAttn",
|
|
"size": "5B",
|
|
"workload": "ti2v",
|
|
"recipe": { "height": 704, "width": 1280, "numFrames": 121, "fps": 24, "numInferenceSteps": 3, "guidanceScale": 5, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": null, "dmdDenoisingSteps": [1000, 757, 522], "attentionBackends": ["FLASH_ATTN", "VIDEO_SPARSE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
|
|
"name": "Wan2.2 TI2V",
|
|
"size": "5B",
|
|
"workload": "ti2v",
|
|
"recipe": { "height": 704, "width": 1280, "numFrames": 121, "fps": 24, "numInferenceSteps": 50, "guidanceScale": 5, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
|
|
"name": "Wan2.2 T2V",
|
|
"size": "A14B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 720, "width": 1280, "numFrames": 81, "fps": 16, "numInferenceSteps": 40, "guidanceScale": 4, "guidanceScale2": 3, "embeddedCfgScale": 6, "flowShift": 12, "boundaryRatio": 0.875, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "Wan-AI/Wan2.2-I2V-A14B-Diffusers",
|
|
"name": "Wan2.2 I2V",
|
|
"size": "A14B",
|
|
"workload": "i2v",
|
|
"recipe": { "height": 832, "width": 480, "numFrames": 81, "fps": 16, "numInferenceSteps": 40, "guidanceScale": 3.5, "guidanceScale2": 3.5, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": 0.9, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "hunyuanvideo-community/HunyuanVideo",
|
|
"name": "HunyuanVideo",
|
|
"size": "13B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 720, "width": 1280, "numFrames": 125, "fps": 24, "numInferenceSteps": 50, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 7, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "FastVideo/FastHunyuan-diffusers",
|
|
"name": "FastHunyuan",
|
|
"size": "13B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 720, "width": 1280, "numFrames": 125, "fps": 24, "numInferenceSteps": 6, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 17, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
|
|
"name": "Wan2.1 T2V",
|
|
"size": "1.3B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 480, "width": 832, "numFrames": 81, "fps": 16, "numInferenceSteps": 50, "guidanceScale": 3, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 3, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "Wan-AI/Wan2.1-T2V-14B-Diffusers",
|
|
"name": "Wan2.1 T2V",
|
|
"size": "14B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 720, "width": 1280, "numFrames": 81, "fps": 16, "numInferenceSteps": 50, "guidanceScale": 5, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers",
|
|
"name": "Wan2.1 I2V 480P",
|
|
"size": "14B",
|
|
"workload": "i2v",
|
|
"recipe": { "height": 480, "width": 832, "numFrames": 81, "fps": 16, "numInferenceSteps": 40, "guidanceScale": 5, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 3, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers",
|
|
"name": "Wan2.1 I2V 720P",
|
|
"size": "14B",
|
|
"workload": "i2v",
|
|
"recipe": { "height": 720, "width": 1280, "numFrames": 81, "fps": 16, "numInferenceSteps": 40, "guidanceScale": 5, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN", "SAGE_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "loayrashid/TurboWan2.1-T2V-1.3B-Diffusers",
|
|
"name": "TurboWan2.1 T2V",
|
|
"size": "1.3B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 480, "width": 832, "numFrames": 81, "fps": 16, "numInferenceSteps": 4, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 3, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["SLA_ATTN"], "defaultAttentionBackend": "SLA_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "loayrashid/TurboWan2.1-T2V-14B-Diffusers",
|
|
"name": "TurboWan2.1 T2V",
|
|
"size": "14B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 720, "width": 1280, "numFrames": 81, "fps": 16, "numInferenceSteps": 4, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["SLA_ATTN"], "defaultAttentionBackend": "SLA_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "loayrashid/TurboWan2.2-I2V-A14B-Diffusers",
|
|
"name": "TurboWan2.2 I2V",
|
|
"size": "A14B",
|
|
"workload": "i2v",
|
|
"recipe": { "height": 720, "width": 1280, "numFrames": 81, "fps": 16, "numInferenceSteps": 4, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": 0.9, "dmdDenoisingSteps": null, "attentionBackends": ["SLA_ATTN"], "defaultAttentionBackend": "SLA_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "FastVideo/LongCat-Video-T2V-Diffusers",
|
|
"name": "LongCat T2V",
|
|
"size": "13.6B",
|
|
"workload": "t2v",
|
|
"recipe": { "height": 480, "width": 848, "numFrames": 121, "fps": 24, "numInferenceSteps": 50, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": null, "boundaryRatio": null, "dmdDenoisingSteps": null, "attentionBackends": ["FLASH_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "FastVideo/Matrix-Game-2.0-Base-Distilled-Diffusers",
|
|
"name": "Matrix Game 2.0 Base",
|
|
"size": "1.3B",
|
|
"workload": "game",
|
|
"keyboardDim": 4,
|
|
"recipe": { "height": 352, "width": 640, "numFrames": 57, "fps": 25, "numInferenceSteps": 3, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": null, "dmdDenoisingSteps": [1000, 666, 333], "attentionBackends": ["FLASH_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "FastVideo/Matrix-Game-2.0-GTA-Distilled-Diffusers",
|
|
"name": "Matrix Game 2.0 GTA",
|
|
"size": "1.3B",
|
|
"workload": "game",
|
|
"keyboardDim": 2,
|
|
"recipe": { "height": 352, "width": 640, "numFrames": 57, "fps": 25, "numInferenceSteps": 3, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": null, "dmdDenoisingSteps": [1000, 666, 333], "attentionBackends": ["FLASH_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
},
|
|
{
|
|
"id": "FastVideo/Matrix-Game-2.0-TempleRun-Distilled-Diffusers",
|
|
"name": "Matrix Game 2.0 TempleRun",
|
|
"size": "1.3B",
|
|
"workload": "game",
|
|
"keyboardDim": 7,
|
|
"usesMouse": false,
|
|
"recipe": { "height": 352, "width": 640, "numFrames": 57, "fps": 25, "numInferenceSteps": 3, "guidanceScale": 1, "guidanceScale2": null, "embeddedCfgScale": 6, "flowShift": 5, "boundaryRatio": null, "dmdDenoisingSteps": [1000, 666, 333], "attentionBackends": ["FLASH_ATTN"], "defaultAttentionBackend": "FLASH_ATTN", "vsaSparsity": 0 }
|
|
}
|
|
]
|
|
}
|