为什么我用默认的工作流生成的图片是这样的。最开始是正常的，后来加载了别人的工作流，安装了很多缺失的插件，最后默认工作流生成后就有问题了。
got prompt
[rgthree] Using rgthree's optimized recursive execution.
[rgthree] First run patching recursive_output_delete_if_changed and recursive_will_execute.
[rgthree] Note: If execution seems broken due to forward ComfyUI changes, you can disable the optimization from rgthree settings in ComfyUI.
model_type EPS
adm 0
Using split attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using split attention in VAE
clip missing: ['clip_l.logit_scale', 'clip_l.transformer.text_projection.weight']
clip unexpected: ['clip_l.transformer.text_model.embeddings.position_ids']
Requested to load SD1ClipModel
Loading 1 new model
Requested to load BaseModel
Loading 1 new model
100%|███████████████████████████████████████████| 22/22 [00:32<00:00, 1.47s/it]
Requested to load AutoencoderKL
Loading 1 new model
Prompt executed in 39.24 seconds

不完整

我查询了这个问题，是由于我的Mac系统升级到了14.4导致的，国外有人测试了不同采样器和调度器的组合可以解决。也有将torchvision降低版本的，conda install torchvision=0.16.2 -c pytorch，但我试验了没有成功。
可以的:
dpmpp_sde / sgm_uniform
dpmpp_sde / normal
euler / ddim_uniform
dpm_sde_gpu / sgm_uniform
dpm_sde_gpu / karras
dpmpp_2m_sde / karras
不行的:
dpmpp_sde / karras
dpmpp_2m / karras
euler, euler_a / normal
euler, euler_a / sgm_uniform
euler / karras
euler / simple
ddim / normal
ddpm / normal
ddpm / karras
heun / normal