valknar/runpod
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: rebuild SVD-XT workflow with correct node types

Browse Source 
- Replace DiffusersLoader with ImageOnlyCheckpointLoader
- Replace SVDSampler with SVD_img2vid_Conditioning + KSampler
- Add VideoLinearCFGGuidance for temporal consistency
- Add all node connections in links array
- Configure VHS_VideoCombine with correct parameters (25 frames)
- Increase steps to 30 for better quality with longer video

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Sebastian Krüger
2025-11-23 10:15:43 +01:00
parent d7bae9cde5
commit 8b4f141d82
1 changed files with 344 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files

447
comfyui/workflows/image-to-video/svd-xt-i2v-production-v1.json
View File

@@ -1,18 +1,13 @@
{
"last_node_id": 8,
"last_node_id": 7,
"last_link_id": 10,
"nodes": [
{
"id": 1,
"type": "LoadImage",
"pos": [
50,
100
],
"widgets_values": [
"input_frame.png",
"image"
],
"pos": [50, 100],
"size": [315, 314],
"widgets_values": ["input_frame.png", "image"],
"title": "API Input Image",
"flags": {},
"order": 0,
@@ -20,157 +15,403 @@
"properties": {
"Node name for S&R": "LoadImage"
},
"size": {
"0": 350,
"1": 100
}
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [1],
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
]
},
{
"id": 2,
"type": "DiffusersLoader",
"pos": [
50,
400
],
"widgets_values": [
"diffusion_models/stable-video-diffusion-img2vid-xt"
],
"type": "ImageOnlyCheckpointLoader",
"pos": [50, 500],
"size": [350, 100],
"widgets_values": ["svd_xt.safetensors"],
"title": "SVD-XT Model Loader",
"flags": {},
"order": 1,
"mode": 0,
"properties": {
"Node name for S&R": "DiffusersLoader"
"Node name for S&R": "ImageOnlyCheckpointLoader"
},
"size": {
"0": 350,
"1": 100
}
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [2],
"slot_index": 0
},
{
"name": "CLIP_VISION",
"type": "CLIP_VISION",
"links": [3],
"slot_index": 1
},
{
"name": "VAE",
"type": "VAE",
"links": [4, 5],
"slot_index": 2
}
]
},
{
"id": 3,
"type": "SVDSampler",
"pos": [
450,
100
],
"widgets_values": [
42,
"fixed",
30,
25,
127,
0.02
],
"title": "SVD-XT Sampler (25 frames)",
"type": "VideoLinearCFGGuidance",
"pos": [450, 500],
"size": [315, 100],
"widgets_values": [1.0],
"title": "Linear CFG Guidance",
"flags": {},
"order": 2,
"mode": 0,
"properties": {
"Node name for S&R": "SVDSampler"
"Node name for S&R": "VideoLinearCFGGuidance"
},
"size": {
"0": 315,
"1": 474
}
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 2
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [6],
"slot_index": 0
}
]
},
{
"id": 4,
"type": "VAEDecode",
"pos": [
800,
100
],
"title": "VAE Decode Video",
"type": "SVD_img2vid_Conditioning",
"pos": [450, 100],
"size": [315, 350],
"widgets_values": [1024, 576, 25, 127, 6, 0.0],
"title": "SVD-XT Image-to-Video Conditioning (25 frames)",
"flags": {},
"order": 3,
"mode": 0,
"properties": {
"Node name for S&R": "VAEDecode"
"Node name for S&R": "SVD_img2vid_Conditioning"
},
"size": {
"0": 315,
"1": 100
}
"inputs": [
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 3
},
{
"name": "init_image",
"type": "IMAGE",
"link": 1
},
{
"name": "vae",
"type": "VAE",
"link": 4
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [7],
"slot_index": 0
},
{
"name": "negative",
"type": "CONDITIONING",
"links": [8],
"slot_index": 1
},
{
"name": "latent",
"type": "LATENT",
"links": [9],
"slot_index": 2
}
]
},
{
"id": 5,
"type": "VHS_VideoCombine",
"pos": [
1100,
100
],
"widgets_values": [
6,
0,
"svd_xt_output",
"video/h264-mp4"
],
"title": "Combine Frames",
"type": "KSampler",
"pos": [800, 100],
"size": [315, 474],
"widgets_values": [42, "fixed", 30, 6.0, "euler", "karras", 1.0],
"title": "KSampler (30 steps)",
"flags": {},
"order": 4,
"mode": 0,
"properties": {
"Node name for S&R": "KSampler"
},
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 6
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 7
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 8
},
{
"name": "latent_image",
"type": "LATENT",
"link": 9
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [10],
"slot_index": 0
}
]
},
{
"id": 6,
"type": "VAEDecode",
"pos": [1150, 100],
"size": [210, 46],
"widgets_values": [],
"title": "VAE Decode Video Frames",
"flags": {},
"order": 5,
"mode": 0,
"properties": {
"Node name for S&R": "VAEDecode"
},
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 10
},
{
"name": "vae",
"type": "VAE",
"link": 5
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [11],
"slot_index": 0
}
]
},
{
"id": 7,
"type": "VHS_VideoCombine",
"pos": [1400, 100],
"size": [315, 200],
"widgets_values": [6, 0, "svd_xt_output", "video/h264-mp4", false, true],
"title": "Combine Video Frames",
"flags": {},
"order": 6,
"mode": 0,
"properties": {
"Node name for S&R": "VHS_VideoCombine"
},
"size": {
"0": 315,
"1": 100
}
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 11
}
],
"outputs": [
{
"name": "Filenames",
"type": "VHS_FILENAMES",
"links": null
}
]
}
],
"links": [],
"links": [
[1, 1, 0, 4, 1, "IMAGE"],
[2, 2, 0, 3, 0, "MODEL"],
[3, 2, 1, 4, 0, "CLIP_VISION"],
[4, 2, 2, 4, 2, "VAE"],
[5, 2, 2, 6, 1, "VAE"],
[6, 3, 0, 5, 0, "MODEL"],
[7, 4, 0, 5, 1, "CONDITIONING"],
[8, 4, 1, 5, 2, "CONDITIONING"],
[9, 4, 2, 5, 3, "LATENT"],
[10, 5, 0, 6, 0, "LATENT"],
[11, 6, 0, 7, 0, "IMAGE"]
],
"groups": [],
"config": {},
"extra": {
"workflow_info": {
"name": "Stable Video Diffusion XT Image-to-Video Production",
"version": "1.0.0",
"version": "1.2.0",
"description": "Extended animation using SVD-XT. Generate 25-frame video for longer animations with smooth motion.",
"category": "image-to-video",
"tags": [
"svd-xt",
"stable-video-diffusion",
"i2v",
"extended",
"production"
],
"tags": ["svd-xt", "stable-video-diffusion", "i2v", "extended", "production"],
"requirements": {
"models": [
"stable-video-diffusion-img2vid-xt"
],
"custom_nodes": [
"ComfyUI-VideoHelperSuite"
],
"vram_min": "18GB"
"models": ["SVD-XT"],
"custom_nodes": ["ComfyUI-VideoHelperSuite"],
"vram_min": "18GB",
"vram_recommended": "20GB"
},
"parameters": {
"input_image": {
"node_id": 1,
"widget_index": 0,
"type": "image",
"required": true
"required": true,
"description": "Starting frame for video generation (1024x576 recommended)"
},
"width": {
"node_id": 4,
"widget_index": 0,
"type": "integer",
"required": false,
"default": 1024,
"min": 16,
"max": 16384,
"description": "Output video width"
},
"height": {
"node_id": 4,
"widget_index": 1,
"type": "integer",
"required": false,
"default": 576,
"min": 16,
"max": 16384,
"description": "Output video height"
},
"video_frames": {
"node_id": 4,
"widget_index": 2,
"type": "integer",
"required": false,
"default": 25,
"min": 1,
"max": 4096,
"description": "Number of frames to generate (25 for SVD-XT)"
},
"motion_bucket_id": {
"node_id": 4,
"widget_index": 3,
"type": "integer",
"required": false,
"default": 127,
"min": 1,
"max": 1023,
"description": "Motion amount (higher = more motion)"
},
"fps": {
"node_id": 4,
"widget_index": 4,
"type": "integer",
"required": false,
"default": 6,
"min": 1,
"max": 1024,
"description": "Frames per second for conditioning"
},
"augmentation_level": {
"node_id": 4,
"widget_index": 5,
"type": "float",
"required": false,
"default": 0.0,
"min": 0.0,
"max": 10.0,
"description": "Noise augmentation level"
},
"steps": {
"node_id": 3,
"node_id": 5,
"widget_index": 2,
"type": "integer",
"default": 30
"required": false,
"default": 30,
"min": 1,
"max": 150,
"description": "Sampling steps (30 recommended)"
},
"frames": {
"node_id": 3,
"type": "integer",
"default": 25,
"description": "Number of output frames"
"cfg": {
"node_id": 5,
"widget_index": 3,
"type": "float",
"required": false,
"default": 6.0,
"min": 0.0,
"max": 30.0,
"description": "Classifier-free guidance scale"
},
"motion_bucket": {
"node_id": 3,
"seed": {
"node_id": 5,
"widget_index": 0,
"type": "integer",
"default": 127
"required": false,
"default": 42,
"description": "Random seed for reproducibility"
},
"output_fps": {
"node_id": 7,
"widget_index": 0,
"type": "integer",
"required": false,
"default": 6,
"description": "Output video framerate"
}
},
"outputs": {
"video": {
"node_id": 7,
"type": "video",
"format": "MP4 (H.264)",
"resolution": "1024x576 (configurable)",
"duration": "~4.2 seconds @ 6fps (25 frames)"
}
},
"performance": {
"avg_generation_time": "40-55 seconds",
"vram_usage": "~16-18GB",
"output": "25 frames (~4.2s @ 6fps)"
}
"vram_usage": "~18-20GB",
"gpu_utilization": "95-100%"
},
"use_cases": [
"Extended animations with smooth motion",
"Longer video loops from single frames",
"Cinematic camera movements",
"Product animation showcases"
],
"notes": [
"SVD-XT generates 25 frames vs 14 frames in base SVD",
"Requires more VRAM (~18GB vs ~16GB)",
"Model auto-downloads on first use (~9GB)",
"Recommended resolution: 1024x576 (16:9)",
"Higher motion_bucket_id = more movement",
"Linear CFG guidance improves temporal consistency"
]
}
},
"version": 0.4
}
}