ChronoEdit 14B:圖像編輯
基於影片模型對圖像的動態理解對圖像進行編輯,創造符合物理規律的新圖像並保持角色和風格的一致性。
關於
ChronoEdit 14B 工作流程透過影片模型的動態理解能力,提供進階影像編輯功能。此工作流程使用 Wan2.1、ChronoEdit 與 Nvidia 等模型,讓編輯結果不只更符合物理合理性,也能在多張圖片之間維持角色與風格一致。其核心能力是以類似處理影片影格的方式來理解圖片,從而進行更連貫、具脈絡的修改。
在技術上,工作流程使用包含 LoadImage 與 SaveImage 的一系列節點來管理影像輸入與輸出。並透過特定 ID 的獨特節點(例如 813daba6-ec1d-42dd-87bc-4f0f6e084a8d 與 2b61e18f-9327-49e6-98af-da8e557c2336)來完成動態編輯處理與套用。這些節點彼此配合,分析影像情境並套用與整體風格及角色一致的修改。因此特別適合需要維持一致視覺敘事的任務,例如角色設計或分鏡開發。
您提供的內容
- 正在讀取工作流程
在 ComfyUI 中執行。 此工作流程無法在此頁面上執行。請在已載入所有內容的 Comfy Cloud 中開啟,或下載到您自己的 ComfyUI。
在 Cloud 中試用此工作流程尚無範例輸出。
工作流程內部
節點圖的唯讀預覽。請在 Comfy Cloud 中開啟,或下載後編輯節點。
Loading the graph
Open full-size workflow preview從程式碼使用此工作流程
可行時會根據工作流程圖和輸入內容產生;否則會顯示儲存的範例。執行可能產生費用的程式碼前,請檢查認證資訊和端點。
What you need
- Runs on
- Comfy Cloud
- 金鑰
- COMFY_API_KEY
需要付費 Cloud 方案與點數。
# Python 3.10+: pip install comfy-sdk==0.4.0
import os
from comfy_sdk import Comfy
api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
"52": {
"class_type": "LoadImage",
"inputs": {
"image": "image_chrono_edit_input_image.png"
},
"_meta": {
"title": "Load Image"
}
},
"60": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "Chrono_Edit_14B",
"images": [
"97:59",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"97:3": {
"class_type": "KSampler",
"inputs": {
"cfg": 4,
"denoise": 1,
"latent_image": [
"97:50",
2
],
"model": [
"97:58",
0
],
"negative": [
"97:50",
1
],
"positive": [
"97:50",
0
],
"sampler_name": "uni_pc",
"scheduler": "simple",
"seed": 859991172109574,
"steps": 20
},
"_meta": {
"title": "KSampler"
}
},
"97:37": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "chrono_edit_14B_fp16.safetensors",
"weight_dtype": "fp8_e4m3fn"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"97:38": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"device": "default",
"type": "wan"
},
"_meta": {
"title": "Load CLIP"
}
},
"97:39": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "wan_2.1_vae.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"97:49": {
"class_type": "CLIPVisionLoader",
"inputs": {
"clip_name": "clip_vision_h.safetensors"
},
"_meta": {
"title": "Load CLIP Vision"
}
},
"97:50": {
"class_type": "WanImageToVideo",
"inputs": {
"batch_size": 1,
"clip_vision_output": [
"97:51",
0
],
"height": 720,
"length": 5,
"negative": [
"97:7",
0
],
"positive": [
"97:6",
0
],
"start_image": [
"52",
0
],
"vae": [
"97:39",
0
],
"width": 720
},
"_meta": {
"title": "WanImageToVideo"
}
},
"97:51": {
"class_type": "CLIPVisionEncode",
"inputs": {
"clip_vision": [
"97:49",
0
],
"crop": "none",
"image": [
"52",
0
]
},
"_meta": {
"title": "CLIP Vision Encode"
}
},
"97:54": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"97:37",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"97:58": {
"class_type": "ScaleROPE",
"inputs": {
"model": [
"97:54",
0
],
"scale_t": 7,
"scale_x": 1,
"scale_y": 1,
"shift_t": 0,
"shift_x": 0,
"shift_y": 0
},
"_meta": {
"title": "ScaleROPE"
}
},
"97:59": {
"class_type": "ImageFromBatch",
"inputs": {
"batch_index": 4,
"image": [
"97:8",
0
],
"length": 1
},
"_meta": {
"title": "Get Image from Batch"
}
},
"97:6": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"97:38",
0
],
"text": "A bottle of facial cleansing foam and bubble shampoo, surrounded by white, round, foamy bubbles. The bubbles are very fluffy, crystal clear, giving a sense of fluffiness and comfort. There are also several bubbles floating in the air around, and the bottle is floating in the air. The background is light pink. The high-resolution picture creates a professional advertising style with high-definition images and high-quality details."
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"97:7": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"97:38",
0
],
"text": "色调艳丽,过曝,静态,细节模糊不清,字幕,风格,作品,画作,画面,静止,整体发灰,最差质量,低质量,JPEG压缩残留,丑陋的,残缺的,多余的手指,画得不好的手部,画得不好的脸部,畸形的,毁容的,形态畸形的肢体,手指融合,静止不动的画面,杂乱的背景,三条腿,背景人很多,倒着走"
},
"_meta": {
"title": "CLIP Text Encode (Negative Prompt)"
}
},
"97:8": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"97:3",
0
],
"vae": [
"97:39",
0
]
},
"_meta": {
"title": "VAE Decode"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)問答
ChronoEdit 14B 利用影片模型的動態特性,讓編輯在影像風格與角色上保持一致;不同於傳統的靜態影像編輯。
它主要是為單張影像設計,但你可以透過自動化 LoadImage 與 SaveImage 節點來改造成批次處理。
此工作流程針對搭載 Nvidia GPU 的系統做了最佳化,以充分發揮 Nvidia 模型能力;也能在其他硬體上執行,但效能會較低。
你可以在特定處理節點中調整相關參數,以微調套用的動態編輯程度與一致性。
相關工作流程
- Wan2.1, ChronoEdit, Nvidia
ChronoEdit 14B:圖像編輯
- Wan2.1, Wan
Wan 2.1 ControlNet
- Wan2.1, Wan
Wan 2.1 Fun Camera 1.3B
- Wan2.1, Wan
Wan 2.1 Fun Camera 14B
- Wan2.1, Wan
Wan 2.1 首尾幀影片 720p F16
- Wan2.1, Wan
Wan ATI
- Wan2.1, Wan
Wan VACE控制影片
- Wan2.1, Wan
Wan2.1 Alpha 文生影片
- Wan2.1, Wan
Wan2.1 VACE 區域性重繪
- Wan2.1, Wan
Wan2.1 VACE 參考生影片
- Wan2.1, Wan
Wan2.1 VACE 擴圖
- Wan2.1, Wan
Wan2.1 VACE 文生影片