aigc-apps / sd-webui-EasyPhoto

📷 EasyPhoto | Your Smart AI Photo Generator.
Apache License 2.0
4.98k stars 399 forks source link

video infer 使用webui正常,使用api推理只能出来一帧画面 #396

Open lxlde opened 9 months ago

lxlde commented 9 months ago

debug发现在采样过程中,batch_size一直为1,webui经过processing.py的process_images()方法后能将batchsize设置为16,但是因为api因为没有初始化modules.scripts.scripts_img2img.alwayson_scripts,在sdwebui的t2i_call()方法中的
for alwayson_scripts in modules.scripts.scripts_img2img.alwayson_scripts: if hasattr(alwayson_scripts, "name"): if alwayson_scripts.name is None: continue if alwayson_scripts.name == "controlnet": p_txt2img.script_args[alwayson_scripts.args_from : alwayson_scripts.args_from + len(controlnet_units)] = controlnet_units if alwayson_scripts.name == "animatediff_easyphoto" and animate_diff_process is not None: p_txt2img.script_args[alwayson_scripts.args_from] = animate_diff_process if "dynamic lora weights" in alwayson_scripts.name:

All LoRAs in the additional prompt will be wrapped with LoraCtlNetwork rather than ExtraNetworkLora.

            p_txt2img.script_args[alwayson_scripts.args_from] = True  # Enable Dynamic Lora Weights
            p_txt2img.script_args[alwayson_scripts.args_from + 1] = loractl_flag 

无法成功设置alwayson_scripts参数,导致 processing.py的process_images()中的 if p.scripts is not None: p.scripts.before_process(p) 不执行,batchsize仍为1,我尝试了将batch_size手动设置为16,仍然报错,希望能得到作者回复解决问题,万分感谢