AI绘画专栏stablediffusion之 SD插件大全 (48)

2023-11-28 09:55:07 浏览数 (2)

1.是什么

所谓的插件是通过下载集成的方式,使得SD在绘画过程中通过API的调用在参数内通过页面设置达到二次渲染出图的过程

2.怎么玩

复制到从网址安装

点击安装即可

安装完重启生效

升级版本

3.在哪下

https://gitcode.net/rubble7343/sd-webui-extensions/raw/master/index.json

下载插件的N种方式

1.直接下载zip安装包

2.git clone

3.从网址安装

4.插件列表安装

备份插件列表

https://github.com/Gerschel/sd_web_ui_preset_utils.git

4.报错怎么办

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument weight in method wrapper_CUDA___slow_conv2d_forward)

Console logs

代码语言:javascript复制
Startup time: 46.8s (prepare environment: 25.9s, import torch: 4.7s, import gradio: 1.0s, setup paths: 0.5s, initialize shared: 0.2s, other imports: 0.5s, setup codeformer: 0.3s, load scripts: 8.4s, create ui: 4.1s, gradio launch: 0.6s, app_started_callback: 0.5s).
Loading VAE weights specified in settings: E:sd-webui-akisd-webui-aki-v4modelsVAEvae-ft-mse-840000-ema-pruned.safetensors
Applying attention optimization: xformers... done.
Model loaded in 6.5s (load weights from disk: 0.6s, create model: 0.9s, apply weights to model: 4.3s, load VAE: 0.4s, calculate empty prompt: 0.1s).
refresh_ui
Restoring base VAE
Applying attention optimization: xformers... done.
VAE weights loaded.
2023-11-25 18:37:19,315 - ControlNet - INFO - Loading model: control_v11f1p_sd15_depth [cfd03158]
2023-11-25 18:37:19,995 - ControlNet - INFO - Loaded state_dict from [E:sd-webui-akisd-webui-aki-v4modelsControlNetcontrol_v11f1p_sd15_depth.pth]
2023-11-25 18:37:19,996 - ControlNet - INFO - controlnet_default_config
2023-11-25 18:37:22,842 - ControlNet - INFO - ControlNet model control_v11f1p_sd15_depth [cfd03158] loaded.
2023-11-25 18:37:23,008 - ControlNet - INFO - Loading preprocessor: depth
2023-11-25 18:37:23,010 - ControlNet - INFO - preprocessor resolution = 896
2023-11-25 18:37:27,343 - ControlNet - INFO - ControlNet Hooked - Time = 8.458001852035522

0: 640x384 1 face, 78.0ms
Speed: 4.0ms preprocess, 78.0ms inference, 29.0ms postprocess per image at shape (1, 3, 640, 384)
2023-11-25 18:37:50,189 - ControlNet - INFO - Loading model from cache: control_v11f1p_sd15_depth [cfd03158]
2023-11-25 18:37:50,192 - ControlNet - INFO - Loading preprocessor: depth
2023-11-25 18:37:50,192 - ControlNet - INFO - preprocessor resolution = 896
2023-11-25 18:37:50,279 - ControlNet - INFO - ControlNet Hooked - Time = 0.22900152206420898
2023-11-25 18:38:30,791 - AnimateDiff - INFO - AnimateDiff process start.
2023-11-25 18:38:30,791 - AnimateDiff - INFO - Loading motion module mm_sd_v15_v2.ckpt from E:sd-webui-akisd-webui-aki-v4extensionssd-webui-animatediffmodelmm_sd_v15_v2.ckpt
2023-11-25 18:38:31,574 - AnimateDiff - INFO - Guessed mm_sd_v15_v2.ckpt architecture: MotionModuleType.AnimateDiffV2
2023-11-25 18:38:33,296 - AnimateDiff - WARNING - Missing keys <All keys matched successfully>
2023-11-25 18:38:34,243 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet middle block.
2023-11-25 18:38:34,245 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet input blocks.
2023-11-25 18:38:34,245 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet output blocks.
2023-11-25 18:38:34,246 - AnimateDiff - INFO - Setting DDIM alpha.
2023-11-25 18:38:34,254 - AnimateDiff - INFO - Injection finished.
2023-11-25 18:38:34,254 - AnimateDiff - INFO - Hacking loral to support motion lora
2023-11-25 18:38:34,254 - AnimateDiff - INFO - Hacking CFGDenoiser forward function.
2023-11-25 18:38:34,254 - AnimateDiff - INFO - Hacking ControlNet.
*** Error completing request
*** Arguments: ('task(8jna2axn6nwg2d4)', '1 sex girl, big breasts, solo, high heels, skirt, thigh strap, squatting, black footwear, long hair, closed eyes, multicolored hair, red hair, black shirt, sleeveless, black skirt, full body, shirt, lips, brown hair, black hair, sleeveless shirt, bare shoulders, crop top, midriff, grey background, simple background, ', 'bad hands, normal quality, ((monochrome)), ((grayscale)), ((strabismus)), ng_deepnegative_v1_75t, (bad-hands-5:1.3), (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad_prompt, badhandv4, EasyNegative, ', [], 20, 'Euler a', 1, 1, 7, 1600, 896, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], <gradio.routes.Request object at 0x0000024A8CCB4670>, 0, False, '', 0.8, -1, False, -1, 0, 0, 0, True, False, {'ad_model': 'face_yolov8n.pt', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Euler a', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Euler a', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, False, 'keyword prompt', 'keyword1, keyword2', 'None', 'textual inversion first', 'None', '0.7', 'None', False, 1.6, 0.97, 0.4, 0, 20, 0, 12, '', True, False, False, False, 512, False, True, ['Face'], False, '{n    "face_detector": "RetinaFace",n    "rules": {n        "then": {n            "face_processor": "img2img",n            "mask_generator": {n                "name": "BiSeNet",n                "params": {n                    "fallback_ratio": 0.1n                }n            }n        }n    }n}', 'None', 40, <animatediff_utils.py.AnimateDiffProcess object at 0x0000024A8CC58940>, False, False, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, None, 'Refresh models', <scripts.animatediff_ui.AnimateDiffProcess object at 0x0000024A3BD73F10>, UiControlNetUnit(enabled=True, module='depth_midas', model='control_v11f1p_sd15_depth [cfd03158]', weight=1, image={'image': array([[[183, 187, 189],
***         [183, 187, 189],
***         [183, 187, 189],
***         ...,
***         [185, 189, 191],
***         [185, 189, 191],
***         [185, 189, 191]],
*** 
***        [[183, 187, 189],
***         [183, 187, 189],
***         [183, 187, 189],
***         ...,
***         [185, 189, 191],
***         [185, 189, 191],
***         [185, 189, 191]],
*** 
***        [[183, 187, 189],
***         [183, 187, 189],
***         [183, 187, 189],
***         ...,
***         [185, 189, 191],
***         [185, 189, 191],
***         [185, 189, 191]],
*** 
***        ...,
*** 
***        [[223, 224, 227],
***         [223, 224, 227],
***         [223, 224, 227],
***         ...,
***         [227, 227, 227],
***         [227, 227, 227],
***         [227, 227, 227]],
*** 
***        [[223, 224, 227],
***         [223, 224, 227],
***         [223, 224, 227],
***         ...,
***         [227, 227, 227],
***         [227, 227, 227],
***         [227, 227, 227]],
*** 
***        [[223, 224, 227],
***         [223, 224, 227],
***         [223, 224, 227],
***         ...,
***         [227, 227, 227],
***         [227, 227, 227],
***         [227, 227, 227]]], dtype=uint8), 'mask': array([[[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
*** 
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
*** 
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
*** 
***        ...,
*** 
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
*** 
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
*** 
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]]], dtype=uint8)}, resize_mode='Crop and Resize', low_vram=False, processor_res=512, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=True, control_mode='Balanced', save_detected_map=True), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=512, threshold_a=64, threshold_b=64, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=512, threshold_a=64, threshold_b=64, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), False, '', 0.5, True, False, '', 'Lerp', False, False, 1, 0.15, False, 'OUT', ['OUT'], 5, 0, 'Bilinear', False, 'Bilinear', False, 'Lerp', '', '', False, False, None, True, '


	

0 人点赞