diff --git a/README.md b/README.md
index f348c03..ba2fcd2 100644
--- a/README.md
+++ b/README.md
@@ -10,6 +10,8 @@ VidXTend (<10G VRAM) | Original (<15G VRAM)
[Recommended complete Workflow](https://github.com/chaojie/ComfyUI_StreamingT2V/blob/main/workflow/wf_final.json)
+
+
[Recommended STAGE 2 Workflow](https://github.com/chaojie/ComfyUI_StreamingT2V/blob/main/workflow/wf_VidXTend.json)
diff --git a/workflow/wf_final.json b/workflow/wf_final.json
index 206de29..b86bc79 100644
--- a/workflow/wf_final.json
+++ b/workflow/wf_final.json
@@ -6,8 +6,8 @@
"id": 7,
"type": "CLIPTextEncode",
"pos": [
- 413,
- 389
+ 837.1779587402339,
+ 399.49742943191524
],
"size": {
"0": 425.27801513671875,
@@ -44,8 +44,8 @@
"id": 5,
"type": "EmptyLatentImage",
"pos": [
- 473,
- 609
+ 897.177958740234,
+ 619.4974294319152
],
"size": {
"0": 315,
@@ -73,60 +73,12 @@
16
]
},
- {
- "id": 4,
- "type": "CheckpointLoaderSimple",
- "pos": [
- 71,
- 192
- ],
- "size": {
- "0": 315,
- "1": 98
- },
- "flags": {},
- "order": 1,
- "mode": 0,
- "outputs": [
- {
- "name": "MODEL",
- "type": "MODEL",
- "links": [
- 10
- ],
- "slot_index": 0
- },
- {
- "name": "CLIP",
- "type": "CLIP",
- "links": [
- 3,
- 5
- ],
- "slot_index": 1
- },
- {
- "name": "VAE",
- "type": "VAE",
- "links": [
- 8
- ],
- "slot_index": 2
- }
- ],
- "properties": {
- "Node name for S&R": "CheckpointLoaderSimple"
- },
- "widgets_values": [
- "Minimalism_v2.0.safetensors"
- ]
- },
{
"id": 10,
"type": "ADE_AnimateDiffLoaderGen1",
"pos": [
- 70,
- 348
+ 494.17795874023426,
+ 358.49742943191524
],
"size": {
"0": 315,
@@ -200,8 +152,8 @@
"id": 8,
"type": "VAEDecode",
"pos": [
- 1209,
- 188
+ 1633.177958740234,
+ 198.49742943191526
],
"size": {
"0": 210,
@@ -236,76 +188,12 @@
"Node name for S&R": "VAEDecode"
}
},
- {
- "id": 14,
- "type": "StreamingT2VLoaderVidXTendModel",
- "pos": [
- 1195,
- 51
- ],
- "size": {
- "0": 315,
- "1": 58
- },
- "flags": {},
- "order": 2,
- "mode": 0,
- "outputs": [
- {
- "name": "VidXTendPipeline",
- "type": "VidXTendPipeline",
- "links": [
- 13
- ],
- "shape": 3,
- "slot_index": 0
- }
- ],
- "properties": {
- "Node name for S&R": "StreamingT2VLoaderVidXTendModel"
- },
- "widgets_values": [
- "cuda"
- ]
- },
- {
- "id": 16,
- "type": "StreamingT2VLoaderEnhanceModel",
- "pos": [
- 2388,
- 49
- ],
- "size": {
- "0": 315,
- "1": 58
- },
- "flags": {},
- "order": 3,
- "mode": 0,
- "outputs": [
- {
- "name": "msxl_model",
- "type": "msxl_model",
- "links": [
- 15
- ],
- "shape": 3,
- "slot_index": 0
- }
- ],
- "properties": {
- "Node name for S&R": "StreamingT2VLoaderEnhanceModel"
- },
- "widgets_values": [
- "cuda"
- ]
- },
{
"id": 11,
"type": "VHS_VideoCombine",
"pos": [
- 2033,
- 199
+ 506.8155148437508,
+ 1074.0633328353877
],
"size": [
315,
@@ -359,7 +247,7 @@
"hidden": false,
"paused": false,
"params": {
- "filename": "AnimateDiff_00038.mp4",
+ "filename": "AnimateDiff_00041.mp4",
"subfolder": "",
"type": "output",
"format": "video/h264-mp4"
@@ -371,8 +259,8 @@
"id": 18,
"type": "VHS_FILENAMES_STRING_StreamingT2V",
"pos": [
- 2402,
- 194
+ 954.9382551757835,
+ 1013.7920571289062
],
"size": {
"0": 277.20001220703125,
@@ -408,8 +296,8 @@
"id": 6,
"type": "CLIPTextEncode",
"pos": [
- 415,
- 186
+ 839.1779587402339,
+ 196.4974294319152
],
"size": {
"0": 422.84503173828125,
@@ -446,8 +334,8 @@
"id": 20,
"type": "VHS_LoadVideoPath",
"pos": [
- 3151.8190696022725,
- 176.27268635142931
+ 1704.7573247780565,
+ 996.0647434803353
],
"size": [
317.4000244140625,
@@ -527,12 +415,180 @@
}
}
},
+ {
+ "id": 17,
+ "type": "StreamingT2VRunEnhanceStep",
+ "pos": [
+ 1290.9382551757844,
+ 1035.792057128906
+ ],
+ "size": {
+ "0": 315,
+ "1": 222
+ },
+ "flags": {},
+ "order": 12,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "msxl_model",
+ "type": "msxl_model",
+ "link": 15
+ },
+ {
+ "name": "low_video_path",
+ "type": "STRING",
+ "link": 18,
+ "widget": {
+ "name": "low_video_path"
+ }
+ }
+ ],
+ "outputs": [
+ {
+ "name": "video_path",
+ "type": "STRING",
+ "links": [
+ 19
+ ],
+ "shape": 3,
+ "slot_index": 0
+ }
+ ],
+ "properties": {
+ "Node name for S&R": "StreamingT2VRunEnhanceStep"
+ },
+ "widgets_values": [
+ "",
+ "A girl smiling",
+ 24,
+ 56,
+ 32,
+ 1280,
+ 720,
+ true
+ ]
+ },
+ {
+ "id": 19,
+ "type": "VHS_VideoCombine",
+ "pos": [
+ 2109.9382551757826,
+ 897.7920571289058
+ ],
+ "size": [
+ 315,
+ 599
+ ],
+ "flags": {},
+ "order": 14,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "images",
+ "type": "IMAGE",
+ "link": 20
+ },
+ {
+ "name": "audio",
+ "type": "VHS_AUDIO",
+ "link": null
+ },
+ {
+ "name": "batch_manager",
+ "type": "VHS_BatchManager",
+ "link": null
+ }
+ ],
+ "outputs": [
+ {
+ "name": "Filenames",
+ "type": "VHS_FILENAMES",
+ "links": null,
+ "shape": 3
+ }
+ ],
+ "properties": {
+ "Node name for S&R": "VHS_VideoCombine"
+ },
+ "widgets_values": {
+ "frame_rate": 25,
+ "loop_count": 0,
+ "filename_prefix": "AnimateDiff",
+ "format": "video/h264-mp4",
+ "pix_fmt": "yuv420p",
+ "crf": 19,
+ "save_metadata": true,
+ "pingpong": false,
+ "save_output": true,
+ "videopreview": {
+ "hidden": false,
+ "paused": false,
+ "params": {
+ "filename": "AnimateDiff_00042.mp4",
+ "subfolder": "",
+ "type": "output",
+ "format": "video/h264-mp4"
+ }
+ }
+ }
+ },
+ {
+ "id": 15,
+ "type": "StreamingT2VRunLongStepVidXTendPipeline",
+ "pos": [
+ 131.8155148437514,
+ 1079.0633328353877
+ ],
+ "size": {
+ "0": 327.6000061035156,
+ "1": 222
+ },
+ "flags": {},
+ "order": 9,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "VidXTendPipeline",
+ "type": "VidXTendPipeline",
+ "link": 13
+ },
+ {
+ "name": "short_video",
+ "type": "IMAGE",
+ "link": 14
+ }
+ ],
+ "outputs": [
+ {
+ "name": "IMAGE",
+ "type": "IMAGE",
+ "links": [
+ 16
+ ],
+ "shape": 3,
+ "slot_index": 0
+ }
+ ],
+ "properties": {
+ "Node name for S&R": "StreamingT2VRunLongStepVidXTendPipeline"
+ },
+ "widgets_values": [
+ "A girl smiling",
+ 24,
+ 50,
+ 9,
+ 1774,
+ "fixed",
+ "worst quality, normal quality, low quality, low res, blurry, text,watermark, logo, banner, extra digits, cropped,jpeg artifacts, signature, username, error,sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting"
+ ]
+ },
{
"id": 3,
"type": "KSampler",
"pos": [
- 863,
- 186
+ 1297.1779587402343,
+ 207.49742943191524
],
"size": {
"0": 315,
@@ -587,171 +643,115 @@
]
},
{
- "id": 17,
- "type": "StreamingT2VRunEnhanceStep",
+ "id": 4,
+ "type": "CheckpointLoaderSimple",
"pos": [
- 2738,
- 216
+ 492.17795874023426,
+ 201.4974294319153
],
"size": {
"0": 315,
- "1": 222
+ "1": 98
},
"flags": {},
- "order": 12,
+ "order": 1,
"mode": 0,
- "inputs": [
- {
- "name": "msxl_model",
- "type": "msxl_model",
- "link": 15
- },
- {
- "name": "low_video_path",
- "type": "STRING",
- "link": 18,
- "widget": {
- "name": "low_video_path"
- }
- }
- ],
"outputs": [
{
- "name": "video_path",
- "type": "STRING",
+ "name": "MODEL",
+ "type": "MODEL",
"links": [
- 19
+ 10
],
- "shape": 3,
"slot_index": 0
+ },
+ {
+ "name": "CLIP",
+ "type": "CLIP",
+ "links": [
+ 3,
+ 5
+ ],
+ "slot_index": 1
+ },
+ {
+ "name": "VAE",
+ "type": "VAE",
+ "links": [
+ 8
+ ],
+ "slot_index": 2
}
],
"properties": {
- "Node name for S&R": "StreamingT2VRunEnhanceStep"
+ "Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
- "",
- "A girl smiling",
- 24,
- 56,
- 32,
- 1280,
- 720,
- true
+ "Minimalism_v2.0.safetensors"
]
},
{
- "id": 19,
- "type": "VHS_VideoCombine",
+ "id": 14,
+ "type": "StreamingT2VLoaderVidXTendModel",
"pos": [
- 3557,
- 78
- ],
- "size": [
- 315,
- 599
- ],
- "flags": {},
- "order": 14,
- "mode": 0,
- "inputs": [
- {
- "name": "images",
- "type": "IMAGE",
- "link": 20
- },
- {
- "name": "audio",
- "type": "VHS_AUDIO",
- "link": null
- },
- {
- "name": "batch_manager",
- "type": "VHS_BatchManager",
- "link": null
- }
- ],
- "outputs": [
- {
- "name": "Filenames",
- "type": "VHS_FILENAMES",
- "links": null,
- "shape": 3
- }
- ],
- "properties": {
- "Node name for S&R": "VHS_VideoCombine"
- },
- "widgets_values": {
- "frame_rate": 25,
- "loop_count": 0,
- "filename_prefix": "AnimateDiff",
- "format": "video/h264-mp4",
- "pix_fmt": "yuv420p",
- "crf": 19,
- "save_metadata": true,
- "pingpong": false,
- "save_output": true,
- "videopreview": {
- "hidden": false,
- "paused": false,
- "params": {
- "filename": "AnimateDiff_00039.mp4",
- "subfolder": "",
- "type": "output",
- "format": "video/h264-mp4"
- }
- }
- }
- },
- {
- "id": 15,
- "type": "StreamingT2VRunLongStepVidXTendPipeline",
- "pos": [
- 1658,
- 204
+ 102.81551484375129,
+ 876.0633328353878
],
"size": {
- "0": 327.6000061035156,
- "1": 222
+ "0": 315,
+ "1": 58
},
"flags": {},
- "order": 9,
+ "order": 2,
"mode": 0,
- "inputs": [
+ "outputs": [
{
"name": "VidXTendPipeline",
"type": "VidXTendPipeline",
- "link": 13
- },
- {
- "name": "short_video",
- "type": "IMAGE",
- "link": 14
- }
- ],
- "outputs": [
- {
- "name": "IMAGE",
- "type": "IMAGE",
"links": [
- 16
+ 13
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
- "Node name for S&R": "StreamingT2VRunLongStepVidXTendPipeline"
+ "Node name for S&R": "StreamingT2VLoaderVidXTendModel"
},
"widgets_values": [
- "A girl smiling",
- 24,
- 50,
- 9,
- 1774,
- "fixed",
- "worst quality, normal quality, low quality, low res, blurry, text,watermark, logo, banner, extra digits, cropped,jpeg artifacts, signature, username, error,sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting"
+ "cuda"
+ ]
+ },
+ {
+ "id": 16,
+ "type": "StreamingT2VLoaderEnhanceModel",
+ "pos": [
+ 940.9382551757835,
+ 868.7920571289058
+ ],
+ "size": {
+ "0": 315,
+ "1": 58
+ },
+ "flags": {},
+ "order": 3,
+ "mode": 0,
+ "outputs": [
+ {
+ "name": "msxl_model",
+ "type": "msxl_model",
+ "links": [
+ 15
+ ],
+ "shape": 3,
+ "slot_index": 0
+ }
+ ],
+ "properties": {
+ "Node name for S&R": "StreamingT2VLoaderEnhanceModel"
+ },
+ "widgets_values": [
+ "cuda"
]
}
],
@@ -893,7 +893,41 @@
"IMAGE"
]
],
- "groups": [],
+ "groups": [
+ {
+ "title": "STAGE 1 (16x256x256 short video)",
+ "bounding": [
+ 482,
+ 122,
+ 1371,
+ 613
+ ],
+ "color": "#3f789e",
+ "font_size": 24
+ },
+ {
+ "title": "STAGE 2 (long 256x256 video)",
+ "bounding": [
+ 93,
+ 802,
+ 739,
+ 881
+ ],
+ "color": "#3f789e",
+ "font_size": 24
+ },
+ {
+ "title": "STAGE 3 (long enhanced video)",
+ "bounding": [
+ 931,
+ 795,
+ 1504,
+ 712
+ ],
+ "color": "#3f789e",
+ "font_size": 24
+ }
+ ],
"config": {},
"extra": {},
"version": 0.4
diff --git a/workflow/wf_final.png b/workflow/wf_final.png
new file mode 100644
index 0000000..6a2bc33
Binary files /dev/null and b/workflow/wf_final.png differ