[Bug]: API调用插件v2v，controlnet is enabled but no input image is given #497
Comments
|
当我使用 stable-diffusion-webui-forge 时，仍然报错： webui版本版本: f0.0.17v1.8.0rc-latest-276-g29be1da7 • python: 3.10.6 • torch: 2.1.2+cu121 • xformers: 0.0.23.post1 • gradio: 3.41.2 • checkpoint: 86618977ac animatediff版本forge/master | b20f751 调用代码import requests
import json
url = "http://127.0.0.1:7890/sdapi/v1/txt2img"
payload = {
"alwayson_scripts": {
"AnimateDiff": {
"args": [
{
"model": "mm_sd15_v3.safetensors",
"format": ["PNG", "MP4"],
"enable": True,
"video_length": 2,
"fps": 2,
"closed_loop": "N",
"batch_size": 2,
"video_path": "D:\\frame",
"mask_path": "D:\\mask"
}
]
},
"controlnet": {
"args": [
{
"control_mode": "Balanced",
"enabled": True,
"generated_image": None,
"guidance_end": 1,
"guidance_start": 0,
"hr_option": "Both",
"image": None,
"input_mode": "batch",
"model": "control_v11p_sd15_inpaint [ebff9138]",
"module": "inpaint_only",
"pixel_perfect": True,
"processor_res": 0.5,
"resize_mode": "Crop and Resize",
"save_detected_map": True,
"threshold_a": 0.5,
"threshold_b": 0.5,
"use_preview_as_input": False,
"weight": 1
}
]
}
},
"batch_size": 8,
"cfg_scale": 7,
"denoising_strength": 0.7,
"height": 1280,
"prompt": "beautiful_lighting,1girl,",
"sampler_name" : "Euler a",
"seed" : -1,
"steps" : 1,
"width" : 720
}
response = requests.post(url, json=payload)
Console logs2024-04-10 21:12:26,805 - AnimateDiff - INFO - AnimateDiff process start.
*** Error running before_process: D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff.py
Traceback (most recent call last):
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\scripts.py", line 795, in before_process
script.before_process(p, *script_args)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff.py", line 63, in before_process
params.set_p(p)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff_ui.py", line 161, in set_p
cn_units = get_controlnet_units(p)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff_utils.py", line 62, in get_controlnet_units
cn_units_dataclass = [ControlNetUnit.from_dict(cn_unit_dict) for cn_unit_dict in cn_units]
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff_utils.py", line 62, in <listcomp>
cn_units_dataclass = [ControlNetUnit.from_dict(cn_unit_dict) for cn_unit_dict in cn_units]
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\lib_controlnet\external_code.py", line 256, in from_dict
**{k: v for k, v in d.items() if k in vars(ControlNetUnit)}
AttributeError: 'ControlNetUnit' object has no attribute 'items'
---
Warning: field infotext in API payload not found in <modules.processing.StableDiffusionProcessingTxt2Img object at 0x000001FE09ADDDE0>.
2024-04-10 21:12:26,812 - ControlNet - INFO - ControlNet Input Mode: batch
*** Error running process: D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\scripts\controlnet.py
Traceback (most recent call last):
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\scripts.py", line 803, in process
script.process(p, *script_args)
File "D:\stable-diffusion-webui\stable-diffusion-webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\scripts\controlnet.py", line 548, in process
self.process_unit_after_click_generate(p, unit, params, *args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\scripts\controlnet.py", line 298, in process_unit_after_click_generate
input_list, resize_mode = self.get_input_data(p, unit, preprocessor, h, w)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\scripts\controlnet.py", line 203, in get_input_data
resize_mode = external_code.resize_mode_from_value(p.resize_mode)
AttributeError: 'StableDiffusionProcessingTxt2Img' object has no attribute 'resize_mode'
---
2024-04-10 21:12:27,105 - AnimateDiff - INFO - Setting DDIM alpha.
2024-04-10 21:12:27,106 - AnimateDiff - INFO - Injecting motion module mm_sd15_v3.safetensors into SD1.5 UNet.
*** Error running process_before_every_sampling: D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\scripts\controlnet.py
Traceback (most recent call last):
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\scripts.py", line 835, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\scripts\controlnet.py", line 555, in process_before_every_sampling
self.process_unit_before_every_sampling(p, unit, self.current_params[i], *args, **kwargs)
KeyError: 0
---
To load target model BaseModel
To load target model MotionWrapper
Begin to load 2 models
Reuse 1 loaded models
Reuse 1 loaded models
[Memory Management] Current Free GPU Memory (MB) = 19894.94873046875
[Memory Management] Model Memory (MB) = 0.0
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 18870.94873046875
[Memory Management] Current Free GPU Memory (MB) = 19894.94873046875
[Memory Management] Model Memory (MB) = 0.0
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 18870.94873046875
Moving model(s) has taken 0.01 seconds
0%| | 0/1 [00:00<?, ?it/s]*** Error executing callback cfg_denoiser_callback for D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff.py
Traceback (most recent call last):
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\script_callbacks.py", line 233, in cfg_denoiser_callback
c.callback(params)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff_infv2v.py", line 89, in animatediff_on_cfg_denoiser
ad_params.text_cond = ad_params.prompt_scheduler.multi_cond(cfg_params.text_cond, prompt_closed_loop)
AttributeError: 'NoneType' object has no attribute 'multi_cond'
---
100%|████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1.18it/s]
*** Error running postprocess_batch_list: D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff.py
Traceback (most recent call last):
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\scripts.py", line 859, in postprocess_batch_list
script.postprocess_batch_list(p, pp, *script_args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff.py", line 85, in postprocess_batch_list
params.prompt_scheduler.save_infotext_img(p)
AttributeError: 'NoneType' object has no attribute 'save_infotext_img'
---
*** Error running postprocess_batch_list: D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\scripts\controlnet.py
Traceback (most recent call last):
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\scripts.py", line 859, in postprocess_batch_list
script.postprocess_batch_list(p, pp, *script_args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions-builtin\sd_forge_controlnet\scripts\controlnet.py", line 561, in postprocess_batch_list
self.process_unit_after_every_sampling(p, unit, self.current_params[i], pp, *args, **kwargs)
KeyError: 0
---
*** Error running postprocess: D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff.py
Traceback (most recent call last):
File "D:\stable-diffusion-webui\stable-diffusion-webui\modules\scripts.py", line 843, in postprocess
script.postprocess(p, processed, *script_args)
File "D:\stable-diffusion-webui\stable-diffusion-webui\extensions\sd-webui-animatediff\scripts\animatediff.py", line 90, in postprocess
params.prompt_scheduler.save_infotext_txt(res)
AttributeError: 'NoneType' object has no attribute 'save_infotext_txt'
---
Total progress: 100%|████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1.58it/s]
Total progress: 100%|████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1.59it/s]forge/master b20f7519 |
|
This PR should fix the problem |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is there an existing issue for this?
Have you read FAQ on README?
What happened?
我通过API调用插件，进行v2v，controlnet不能正常工作
Steps to reproduce the problem
import requests
import json
url = "http://127.0.0.1:7890/sdapi/v1/txt2img"
payload = {
"alwayson_scripts": {
"AnimateDiff": {
"args": [
{
"model": "mm_sd15_v3.safetensors",
"format": ["PNG", "MP4"],
"enable": True,
"video_length": 1,
"fps": 1,
"closed_loop": "N",
"batch_size": 1,
"video_path": "D:/frame",
"mask_path": "D:/mask"
}
]
},
"controlnet": {
"args": [
{
"enabled": True,
"model": "control_v11p_sd15_inpaint [ebff9138]",
"module": "inpaint_only",
"pixel_perfect": True,
"weight": 1
}
]
}
},
"batch_size": 8,
"cfg_scale": 7,
"denoising_strength": 0.7,
"height": 1280,
"prompt": "beautiful_lighting,1girl,",
"sampler_name" : "Euler a",
"seed" : -1,
"steps" : 1,
"width" : 720
}
response = requests.post(url, json=payload)
What should have happened?
正常通过controlnet控制生成动画
Commit where the problem happens
webui: 版本: v1.8.0 • python: 3.10.6 • torch: 2.1.2+cu121 • xformers: 0.0.23.post1 • gradio: 3.41.2 • checkpoint: 86618977ac
extension: master | a81565d
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
set COMMANDLINE_ARGS=--port 7890 ^ --listen ^ --enable-insecure-extension-access ^ --xformers ^ --apiConsole logs
Additional information
No response
The text was updated successfully, but these errors were encountered: