ComfyUI 使用小结

写在前面

这几天一直在倒腾ComfyUI，能自己调整工作流生成图形确实让人很兴奋。试用下来，发现里面涉及的东西有点多，搞得眼花缭乱。一个是模型多，每个模型都有差异，而且还很占用内存；每个模型又像是一个黑匣子，而且影响结果的因素也多多，有时候甚至不知道是自己描述的问题，还是参数调节的原因，总是会出现一些奇奇怪怪的结果。总之，要想深入下去，受苦受累是少不了的~~~

建议：对于普通人来讲，用这个来尝鲜还是可以的,可以通过这个来了解stable diffusion大概原理。但是不要陷入进去，主要是太消耗时间。

节点解释

概览

• CheckpointLoader：加载Stable Diffusion模型
• CLIP：在Stable Diffusion中用于将文本编码为主模型可以理解的格式。分为正面提示馈、负面提示。
• sampler：使用Stable Diffusion主模型和CLIP中的正反馈、负反馈作为输入来生成图像
• Latent Image：潜在图像，sampler使用它作为输入，通过在其上添加噪音，然后使用正面和负面提示在每个sampler中传递给模型，并用于指导去噪，（文生图的时候使用Empty Latent Image）。
• VAE：用于将图像从潜在空间（Stable Diffusion能理解的格式空间）转换到像素空间（人可以理解）。
• SaveImage node：保存图片的节点。

sampler节点说明

很多微调都在这里操作，这里具体再说明下，

• add_noise: enable ：向图片中添加随机噪声，以便模型对其进行去噪处理
• noise_seed：随机噪音数
• steps ： 你希望正负CLIP提示通过的迭代次数。每一步都会根据Stable Diffusion模型训练所“认为”的内容，增加（正面提示）或移除（负面提示）像素。
• control_after_generate：每次工作流程任务完成后生成一个新的随机种子
• cfg ： 控制SD对提示的遵循程度。较低的cfg值会产生更具创意但往往较为模糊的结果；较高的cfg值（最大值推荐为10）会根据CLIP提示产生更严格的结果。cfg值过高也可能导致“过冲”，即图片边缘变得更为突出，常以不自然的方式强调细节。
• sampler_name ：采样器类型。不同的采样器和调度器在较少步数下表现更好，而有些在较高步数下效果更佳。这需要你自己进行实验！
• scheduler ： 用于选择去噪图片时间步的算法/方法。
• return_with_leftover_noise: enable ：将潜在图像数据及其所有剩余噪声传递给下一个KSampler节点。

• start_at_step ： KSampler开始其去噪图片过程或“去除随机噪声以揭示图片”的步数。第一个KSampler通常从步数0开始。从步数0开始等同于在常规采样器节点中设置去噪率为1.0。
• end_at_step ： KSampler停止去噪图片过程的步数。如果有任何剩余噪声并且启用了带剩余噪声返回，那么它会将剩余噪声传递给下一个KSampler

小技巧

关于提示词

• (word) ：将提示词放入()，可以提示影响。等价(word:1.1)
• (word:1.2)：指定影响权重，太高也可能会出现问题
• {word1 | word2}：随机选择一个作为提示词，使用的时候需要转义，如：{word1 | word2}
• 提示词尽量简单

生成图片

点击Queue Prompt或在键盘上按下Ctrl+Enter 生成图片，

---

预览图形

--preview-method

模型下载地址

这里直接贴是comfyUI 上面列的，后期发现新的再补充。模型文件一般很大，建议下载少部分，自己试用。如果因为网络问题无法下载，可以留言.

# Checkpoints

### SDXL
### I recommend these workflow examples: https://comfyanonymous.github.io/ComfyUI_examples/sdxl/

 wget -c https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors -P ./models/checkpoints/
 wget -c https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/resolve/main/sd_xl_refiner_1.0.safetensors -P ./models/checkpoints/

# SDXL ReVision
 wget -c https://huggingface.co/comfyanonymous/clip_vision_g/resolve/main/clip_vision_g.safetensors -P ./models/clip_vision/

# SD1.5
!wget -c https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt -P ./models/checkpoints/

# SD2
 wget -c https://huggingface.co/stabilityai/stable-diffusion-2-1-base/resolve/main/v2-1_512-ema-pruned.safetensors -P ./models/checkpoints/
 wget -c https://huggingface.co/stabilityai/stable-diffusion-2-1/resolve/main/v2-1_768-ema-pruned.safetensors -P ./models/checkpoints/

# Some SD1.5 anime style
 wget -c https://huggingface.co/WarriorMama777/OrangeMixs/resolve/main/Models/AbyssOrangeMix2/AbyssOrangeMix2_hard.safetensors -P ./models/checkpoints/
 wget -c https://huggingface.co/WarriorMama777/OrangeMixs/resolve/main/Models/AbyssOrangeMix3/AOM3A1_orangemixs.safetensors -P ./models/checkpoints/
 wget -c https://huggingface.co/WarriorMama777/OrangeMixs/resolve/main/Models/AbyssOrangeMix3/AOM3A3_orangemixs.safetensors -P ./models/checkpoints/
 wget -c https://huggingface.co/Linaqruf/anything-v3.0/resolve/main/anything-v3-fp16-pruned.safetensors -P ./models/checkpoints/

# Waifu Diffusion 1.5 (anime style SD2.x 768-v)
 wget -c https://huggingface.co/waifu-diffusion/wd-1-5-beta3/resolve/main/wd-illusion-fp16.safetensors -P ./models/checkpoints/


# unCLIP models
 wget -c https://huggingface.co/comfyanonymous/illuminatiDiffusionV1_v11_unCLIP/resolve/main/illuminatiDiffusionV1_v11-unclip-h-fp16.safetensors -P ./models/checkpoints/
 wget -c https://huggingface.co/comfyanonymous/wd-1.5-beta2_unCLIP/resolve/main/wd-1-5-beta2-aesthetic-unclip-h-fp16.safetensors -P ./models/checkpoints/


# VAE
!wget -c https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors -P ./models/vae/
 wget -c https://huggingface.co/WarriorMama777/OrangeMixs/resolve/main/VAEs/orangemix.vae.pt -P ./models/vae/
 wget -c https://huggingface.co/hakurei/waifu-diffusion-v1-4/resolve/main/vae/kl-f8-anime2.ckpt -P ./models/vae/


# Loras
 wget -c https://civitai.com/api/download/models/10350 -O ./models/loras/theovercomer8sContrastFix_sd21768.safetensors #theovercomer8sContrastFix SD2.x 768-v
 wget -c https://civitai.com/api/download/models/10638 -O ./models/loras/theovercomer8sContrastFix_sd15.safetensors #theovercomer8sContrastFix SD1.x
 wget -c https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_offset_example-lora_1.0.safetensors -P ./models/loras/ #SDXL offset noise lora


# T2I-Adapter
 wget -c https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_depth_sd14v1.pth -P ./models/controlnet/
 wget -c https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_seg_sd14v1.pth -P ./models/controlnet/
 wget -c https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_sketch_sd14v1.pth -P ./models/controlnet/
 wget -c https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_keypose_sd14v1.pth -P ./models/controlnet/
 wget -c https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_openpose_sd14v1.pth -P ./models/controlnet/
 wget -c https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_color_sd14v1.pth -P ./models/controlnet/
 wget -c https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_canny_sd14v1.pth -P ./models/controlnet/

# T2I Styles Model
 wget -c https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_style_sd14v1.pth -P ./models/style_models/

# CLIPVision model (needed for styles model)
 wget -c https://huggingface.co/openai/clip-vit-large-patch14/resolve/main/pytorch_model.bin -O ./models/clip_vision/clip_vit14.bin


# ControlNet
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11e_sd15_ip2p_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11e_sd15_shuffle_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_canny_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11f1p_sd15_depth_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_inpaint_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_lineart_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_mlsd_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_normalbae_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_openpose_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_scribble_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_seg_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15_softedge_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11p_sd15s2_lineart_anime_fp16.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11u_sd15_tile_fp16.safetensors -P ./models/controlnet/

# ControlNet SDXL
 wget -c https://huggingface.co/stabilityai/control-lora/resolve/main/control-LoRAs-rank256/control-lora-canny-rank256.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/stabilityai/control-lora/resolve/main/control-LoRAs-rank256/control-lora-depth-rank256.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/stabilityai/control-lora/resolve/main/control-LoRAs-rank256/control-lora-recolor-rank256.safetensors -P ./models/controlnet/
 wget -c https://huggingface.co/stabilityai/control-lora/resolve/main/control-LoRAs-rank256/control-lora-sketch-rank256.safetensors -P ./models/controlnet/

# GLIGEN
 wget -c https://huggingface.co/comfyanonymous/GLIGEN_pruned_safetensors/resolve/main/gligen_sd14_textbox_pruned_fp16.safetensors -P ./models/gligen/

# ESRGAN upscale model
 wget -c https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P ./models/upscale_models/
 wget -c https://huggingface.co/sberbank-ai/Real-ESRGAN/resolve/main/RealESRGAN_x2.pth -P ./models/upscale_models/
 wget -c https://huggingface.co/sberbank-ai/Real-ESRGAN/r
 esolve/main/RealESRGAN_x4.pth -P ./models/upscale_models/

参考资料：

github.com/comfyanonym…

更多内容请关注公众号Leo4