-
Notifications
You must be signed in to change notification settings - Fork 2
Expand file tree
/
Copy pathkeyframes.json
More file actions
166 lines (166 loc) · 7.27 KB
/
Copy pathkeyframes.json
File metadata and controls
166 lines (166 loc) · 7.27 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
{
"id": "LTX2Keyframes",
"description": "Pinning the first and last frames and letting the model fill in the motion between them. The keyframes are conditions - objects built from the arguments the workflow names, each with the latent index it lands on.",
"summary": "LTX-2.5 video with audio between two supplied stills, pinned as the first and last frames.",
"traits": ["has-audio", "image-conditioned", "needs-input-media"],
"cost_drivers": ["num_frames", "width", "height"],
"variables": {
"transformer_weights_dtype": "{uint4}",
"text_encoder_weights_dtype": "{int8}",
"prompt": "prompt:ltx2/polaroid_lighthouse",
"negative_prompt": "constant:diffusers.pipelines.ltx2.utils.DEFAULT_NEGATIVE_PROMPT",
"width": 960,
"height": 544,
"num_frames": 121,
"frame_rate": 24.0,
"first_image": {
"location": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_first_frame.png"
},
"last_image": {
"location": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_last_frame.png"
}
},
"variable_constraints": {
"num_frames": {
"modulus": 8,
"remainder": 1,
"min_frames": 9,
"reason": "LTX-2.5's video VAE encodes 8 * n + 1 frames, so an off-grid count is not refused by the pipeline but floored to the grid below - a shorter clip than the one asked for. Refused here instead: no 'snap', because rounding a length the other way from the pipeline's own would be a second silent change"
}
},
"seed": 42,
"steps": [
{
"name": "keyframes_to_video",
"pipeline": {
"configuration": {
"component_type": "LTX2ConditionPipeline",
"pre_load_modules": [
"sdnq"
],
"components": {
"transformer": {
"device": "cuda"
},
"text_encoder": {
"group_offload": {
"offload_type": "leaf_level",
"use_stream": true
}
},
"connectors": {
"group_offload": {
"offload_type": "leaf_level",
"use_stream": true
}
},
"vae": {
"device": "cuda"
},
"audio_vae": {
"device": "cuda"
},
"vocoder": {
"device": "cuda"
},
"duration_head": {
"device": "cuda"
}
}
},
"from_pretrained_arguments": {
"model_name": "Lightricks/LTX-2.5-Diffusers",
"torch_dtype": "torch.bfloat16"
},
"transformer": {
"configuration": {
"component_type": "LTX2VideoTransformer3DModel",
"preserve_device_placement": true
},
"quantization_config": {
"configuration": {
"config_type": "sdnq.SDNQConfig"
},
"arguments": {
"weights_dtype": "variable:transformer_weights_dtype",
"quantization_device": "cuda",
"return_device": "cuda",
"use_quantized_matmul": true,
"dequantize_fp32": false
}
},
"from_pretrained_arguments": {
"model_name": "Lightricks/LTX-2.5-Diffusers",
"subfolder": "transformer",
"torch_dtype": "torch.bfloat16"
}
},
"text_encoder": {
"configuration": {
"component_type": "transformers.Gemma4UnifiedForConditionalGeneration",
"preserve_device_placement": true
},
"quantization_config": {
"configuration": {
"config_type": "sdnq.SDNQConfig"
},
"arguments": {
"weights_dtype": "variable:text_encoder_weights_dtype",
"quantization_device": "cuda",
"return_device": "cpu",
"dequantize_fp32": false,
"modules_to_not_convert": [
"embed_vision",
"embed_audio",
"lm_head"
]
}
},
"from_pretrained_arguments": {
"model_name": "Lightricks/LTX-2.5-Diffusers",
"subfolder": "text_encoder",
"torch_dtype": "torch.bfloat16"
}
},
"arguments": {
"prompt": "variable:prompt",
"negative_prompt": "variable:negative_prompt",
"width": "variable:width",
"height": "variable:height",
"num_frames": "variable:num_frames",
"frame_rate": "variable:frame_rate",
"sigmas": "constant:diffusers.pipelines.ltx2.utils.DISTILLED_SIGMA_VALUES",
"guidance_scale": 1.0,
"audio_guidance_scale": 1.0,
"stg_scale": 0.0,
"audio_stg_scale": 0.0,
"modality_scale": 1.0,
"audio_modality_scale": 1.0,
"output_type": "{np}",
"conditions": [
{
"condition_type": "diffusers.pipelines.ltx2.pipeline_ltx2_condition.LTX2VideoCondition",
"from_arguments": {
"frames": "variable:first_image",
"index": 0,
"strength": 1.0
}
},
{
"condition_type": "diffusers.pipelines.ltx2.pipeline_ltx2_condition.LTX2VideoCondition",
"from_arguments": {
"frames": "variable:last_image",
"index": -1,
"strength": 1.0
}
}
]
}
},
"result": {
"content_type": "video/mp4",
"fps": 24
}
}
]
}