comyui如何实现对图片局部重绘?
网友回复
这个工作流就是comyui图片局部重绘工作流,先保存为json文件,再在comyui中打开
{ "last_node_id": 72, "last_link_id": 26, "nodes": [ { "id": 63, "type": "VAELoader", "pos": [ 120, 630 ], "size": { "0": 315, "1": 58 }, "flags": {}, "order": 0, "mode": 0, "outputs": [ { "name": "VAE", "type": "VAE", "links": [ 14, 17 ], "shape": 3, "slot_index": 0 } ], "properties": { "Node name for S&R": "VAELoader" }, "widgets_values": [ "vae-ft-mse-840000-ema-pruned.safetensors" ], "_widget_cache_map": {}, "category": "Primitive Nodes" }, { "id": 65, "type": "VAEEncodeForInpaint", "pos": [ 508, 629 ], "size": { "0": 226.8000030517578, "1": 98 }, "flags": {}, "order": 8, "mode": 0, "inputs": [ { "name": "pixels", "type": "IMAGE", "link": 16, "label": "图像" }, { "name": "vae", "type": "VAE", "link": 17, "label": "VAE" }, { "name": "mask", "type": "MASK", "link": 18, "label": "遮罩" } ], "outputs": [ { "name": "LATENT", "type": "LATENT", "links": [ 12 ], "shape": 3, "slot_index": 0, "label": "Latent" } ], "properties": { "Node name for S&R": "VAEEncodeForInpaint" }, "widgets_values": [ 12 ], "_widget_cache_map": {}, "category": "Primitive Nodes" }, { "id": 6, "type": "CLIPTextEncode", "pos": [ 441, 90 ], "size": { "0": 370, "1": 160 }, "flags": {}, "order": 6, "mode": 0, "inputs": [ { "name": "clip", "type": "CLIP", "link": 3, "label": "CLIP" } ], "outputs": [ { "name": "CONDITIONING", "type": "CONDITIONING", "links": [ 20, 23 ], "slot_index": 0, "label": "条件" } ], "properties": { "Node name for S&R": "CLIPTextEncode" }, "widgets_values": [ "beautiful scenery nature glass bottle landscape, , purple galaxy bottle," ], "_widget_cache_map": {}, "color": "#232", "bgcolor": "#353", "category": "Primitive Nodes" }, { "id": 7, "type": "CLIPTextEncode", "pos": [ 438, 301 ], "size": { "0": 370, "1": 160 }, "flags": {}, "order": 7, "mode": 0, "inputs": [ { "name": "clip", "type": "CLIP", "link": 5, "label": "CLIP" } ], "outputs": [ { "name": "CONDITIONING", "type": "CONDITIONING", "links": [ 21, 24 ], "slot_index": 0, "label": "条件" } ], "properties": { "Node name for S&R": "CLIPTextEncode" }, "widgets_values": [ "text, watermark,horror,zombie, nsfw," ], "_widget_cache_map": {}, "color": "#322", "bgcolor": "#533", "category": "Primitive Nodes" }, { "id": 59, "type": "KSampler", "pos": [ 836, 92 ], "size": { "0": 300, "1": 474 }, "flags": {}, "order": 9, "mode": 0, "inputs": [ { "name": "model", "type": "MODEL", "link": 22, "label": "模型" }, { "name": "positive", "type": "CONDITIONING", "link": 20, "label": "正面条件" }, { "name": "negative", "type": "CONDITIONING", "link": 21, "label": "负面条件" }, { "name": "latent_image", "type": "LATENT", "link": 12, "label": "Latent" } ], "outputs": [ { ...
点击查看剩余70%
python如何压缩视频到指定的分辨率大小?
抖音微信小程序有压缩视频分辨率的api吗?
ollama中的deepseek有没有本地越狱提示词?
deepseek r1各个版本本地电脑部署运行的硬件要求是多少?
python如何分离视频中的音频与视频为mp4与wav文件?
python报错: ImportError: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the ‘ssl‘ module is comp
ps支持命令行执行脚本文件修改图片吗?
传统的个人博客站长如何应对ai搜索的流量锐减?
centos安装python3.10提示ssl模块不存在?
deepseek r1如何使用本地gpu运行?