Update README.md
Browse files
README.md
CHANGED
|
@@ -131,18 +131,19 @@ If this helped you out, leave a heart or start a discussion on what should be ad
|
|
| 131 |
│ ├── RealESRGAN_x2plus.pth
|
| 132 |
</details>
|
| 133 |
|
| 134 |
-
|
| 135 |
-
- UNETs: Dev, Schnell, Depth, Canny, Fill
|
| 136 |
-
- GGUFs: Q3/Q5/Q6 + FP8
|
| 137 |
-
- CLIP + T5XXL encoders
|
| 138 |
|
| 139 |
-
|
| 140 |
-
- Checkpoints: Inpainting models, Hyper3d (Merged created by Maxed Out) and Sdxl Real Dream 6
|
| 141 |
-
- ControlNets: Depth, Canny, OpenPose, etc.
|
| 142 |
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
|
| 147 |
---
|
| 148 |
|
|
@@ -157,7 +158,7 @@ If this helped you out, leave a heart or start a discussion on what should be ad
|
|
| 157 |
|
| 158 |
## 👇 Showcase
|
| 159 |
|
| 160 |
-
🧠 Depth:
|
| 161 |
|
| 162 |
Flux Depth uses the depth map of an image, letting you prompt for what to fill it with. It's great for keeping the spatial layout while restyling the image however you want.
|
| 163 |
|
|
@@ -168,7 +169,7 @@ Flux Depth uses the depth map of an image, letting you prompt for what to fill i
|
|
| 168 |
|
| 169 |

|
| 170 |
|
| 171 |
-
✏️ Canny:
|
| 172 |
|
| 173 |
Flux Canny uses an edge map and also lets you prompt freely. It’s especially good for repurposing parts of an image like the planet in the first example.
|
| 174 |
|
|
@@ -178,7 +179,7 @@ Flux Canny uses an edge map and also lets you prompt freely. It’s especially g
|
|
| 178 |
|
| 179 |

|
| 180 |
|
| 181 |
-
|
| 182 |
|
| 183 |
Self-explanatory. It’s great when you don’t want Depth or Canny getting distracted by other elements in the original image.
|
| 184 |
|
|
@@ -189,7 +190,7 @@ Self-explanatory. It’s great when you don’t want Depth or Canny getting dist
|
|
| 189 |

|
| 190 |
|
| 191 |
|
| 192 |
-
🫠 Pulid Face Transfer
|
| 193 |
|
| 194 |
Pulid lets you use a face as a reference and prompt as usual. The result will keep a rough match of the reference face. It’s pretty solid without needing any training, though not perfect. As you can see, it struggled with Aloy’s hair.
|
| 195 |
|
|
@@ -199,7 +200,9 @@ Pulid lets you use a face as a reference and prompt as usual. The result will ke
|
|
| 199 |
|
| 200 |

|
| 201 |
|
| 202 |
-
🔄 Redux
|
|
|
|
|
|
|
| 203 |
|
| 204 |

|
| 205 |
|
|
@@ -207,5 +210,5 @@ Pulid lets you use a face as a reference and prompt as usual. The result will ke
|
|
| 207 |
|
| 208 |

|
| 209 |
|
| 210 |
-
|
| 211 |
|
|
|
|
| 131 |
│ ├── RealESRGAN_x2plus.pth
|
| 132 |
</details>
|
| 133 |
|
| 134 |
+
## New to ComfyUI or just want clean workflows?
|
|
|
|
|
|
|
|
|
|
| 135 |
|
| 136 |
+
Flux:
|
|
|
|
|
|
|
| 137 |
|
| 138 |
+

|
| 139 |
+
|
| 140 |
+
[Available on the Maxed Out Patreon (free, no paywall)](https://www.patreon.com/posts/flux-level-1-and-131945103?utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=postshare_creator&utm_content=join_link)
|
| 141 |
+
|
| 142 |
+
SDXL:
|
| 143 |
+
|
| 144 |
+

|
| 145 |
+
|
| 146 |
+
[Available on the Maxed Out Patreon (free, no paywall)](https://www.patreon.com/posts/sdxl-v1-5-just-129782694?utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=postshare_creator&utm_content=join_link)
|
| 147 |
|
| 148 |
---
|
| 149 |
|
|
|
|
| 158 |
|
| 159 |
## 👇 Showcase
|
| 160 |
|
| 161 |
+
## 🧠 Depth:
|
| 162 |
|
| 163 |
Flux Depth uses the depth map of an image, letting you prompt for what to fill it with. It's great for keeping the spatial layout while restyling the image however you want.
|
| 164 |
|
|
|
|
| 169 |
|
| 170 |

|
| 171 |
|
| 172 |
+
## ✏️ Canny:
|
| 173 |
|
| 174 |
Flux Canny uses an edge map and also lets you prompt freely. It’s especially good for repurposing parts of an image like the planet in the first example.
|
| 175 |
|
|
|
|
| 179 |
|
| 180 |

|
| 181 |
|
| 182 |
+
##🕺 OpenPose:
|
| 183 |
|
| 184 |
Self-explanatory. It’s great when you don’t want Depth or Canny getting distracted by other elements in the original image.
|
| 185 |
|
|
|
|
| 190 |

|
| 191 |
|
| 192 |
|
| 193 |
+
## 🫠 Pulid Face Transfer
|
| 194 |
|
| 195 |
Pulid lets you use a face as a reference and prompt as usual. The result will keep a rough match of the reference face. It’s pretty solid without needing any training, though not perfect. As you can see, it struggled with Aloy’s hair.
|
| 196 |
|
|
|
|
| 200 |
|
| 201 |

|
| 202 |
|
| 203 |
+
## 🔄 Redux
|
| 204 |
+
|
| 205 |
+
Use the style of one image to influence another.
|
| 206 |
|
| 207 |

|
| 208 |
|
|
|
|
| 210 |
|
| 211 |

|
| 212 |
|
| 213 |
+
|
| 214 |
|