Text-to-Image
GGUF
English
wan 2.2
text to image
upscale
inpainting
controlnet
depth
canny
redux
comfyui
flux
krea
sdxl
kontext
nunchuka
Instructions to use MaxedOut/ComfyUI-Starter-Packs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use MaxedOut/ComfyUI-Starter-Packs with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="MaxedOut/ComfyUI-Starter-Packs", filename="Flux1/clip/GGUF/t5xxl_Q5_K_M.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use MaxedOut/ComfyUI-Starter-Packs with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M # Run inference directly in the terminal: llama-cli -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M # Run inference directly in the terminal: llama-cli -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
Use Docker
docker model run hf.co/MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use MaxedOut/ComfyUI-Starter-Packs with Ollama:
ollama run hf.co/MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
- Unsloth Studio
How to use MaxedOut/ComfyUI-Starter-Packs with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MaxedOut/ComfyUI-Starter-Packs to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MaxedOut/ComfyUI-Starter-Packs to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for MaxedOut/ComfyUI-Starter-Packs to start chatting
- Docker Model Runner
How to use MaxedOut/ComfyUI-Starter-Packs with Docker Model Runner:
docker model run hf.co/MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
- Lemonade
How to use MaxedOut/ComfyUI-Starter-Packs with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MaxedOut/ComfyUI-Starter-Packs:Q4_K_M
Run and chat with the model
lemonade run user.ComfyUI-Starter-Packs-Q4_K_M
List all available models
lemonade list
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,10 +28,20 @@ pipeline_tag: text-to-image
|
|
| 28 |
|
| 29 |
---
|
| 30 |
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
βββ Flux1
|
| 36 |
β βββ Controlnets
|
| 37 |
β β βββ flux_shakker_labs_union_pro-fp16.safetensors
|
|
@@ -81,10 +91,7 @@ Edit
|
|
| 81 |
β β βββ ae.safetensors
|
| 82 |
</details>
|
| 83 |
|
| 84 |
-
<details> <summary>π¨ SDXL
|
| 85 |
-
go
|
| 86 |
-
Copy
|
| 87 |
-
Edit
|
| 88 |
βββ SDXL
|
| 89 |
β βββ checkpoints
|
| 90 |
β β βββ Hyper3d.safetensors
|
|
@@ -102,9 +109,7 @@ Edit
|
|
| 102 |
β β βββ sdxl_vae.safetensors
|
| 103 |
</details>
|
| 104 |
|
| 105 |
-
<details> <summary>π§ ADetailer
|
| 106 |
-
Copy
|
| 107 |
-
Edit
|
| 108 |
βββ Adetailer
|
| 109 |
β βββ Ultralytics
|
| 110 |
β β βββ bbox
|
|
@@ -114,35 +119,18 @@ Edit
|
|
| 114 |
β β βββ sam_vit_b_01ec64.pth
|
| 115 |
</details>
|
| 116 |
|
| 117 |
-
<details> <summary>π€ Face Restore
|
| 118 |
-
Copy
|
| 119 |
-
Edit
|
| 120 |
βββ FaceRestore_Models
|
| 121 |
β βββ GFPGANv1.4.pth
|
| 122 |
β βββ codeformer.pth
|
| 123 |
</details>
|
| 124 |
|
| 125 |
-
<details> <summary>π Upscale
|
| 126 |
-
Copy
|
| 127 |
-
Edit
|
| 128 |
βββ Upscale_Models
|
| 129 |
β βββ 4x-UltraSharp.pth
|
| 130 |
β βββ RealESRGAN_x2plus.pth
|
| 131 |
</details>
|
| 132 |
|
| 133 |
-
# ComfyUI-Starter-Packs
|
| 134 |
-
|
| 135 |
-
A curated vault of essential models for ComfyUI users β organized, curated, and ready.
|
| 136 |
-
No bloat. No hunting through 15 pages of Civitai and Hugging Face repos.
|
| 137 |
-
|
| 138 |
-
---
|
| 139 |
-
### I See You ποΈ
|
| 140 |
-
|
| 141 |
-
Downloads keep rising⦠but with zero hearts or comments, I have no idea if I'm helping anyone or just feeding a download bot farm in silence.
|
| 142 |
-
If this helped you out, leave a heart or start a discussion on what should be added next β otherwise Iβll assume I built this for the void (and a very busy botnet).
|
| 143 |
-
|
| 144 |
-
## π¦ Whatβs Inside
|
| 145 |
-
|
| 146 |
### `Flux/`
|
| 147 |
- UNETs: Dev, Schnell, Depth, Canny, Fill
|
| 148 |
- GGUFs: Q3/Q5/Q6 + FP8
|
|
@@ -158,12 +146,6 @@ If this helped you out, leave a heart or start a discussion on what should be ad
|
|
| 158 |
|
| 159 |
---
|
| 160 |
|
| 161 |
-
## β οΈ Heads Up
|
| 162 |
-
|
| 163 |
-
- This repo is will get new sections for new models. Go to the community tab, start a discussion, and let me know what you would like added.
|
| 164 |
-
|
| 165 |
-
---
|
| 166 |
-
|
| 167 |
## π Want the Easy Button?
|
| 168 |
|
| 169 |
**[Join Patreon](https://www.patreon.com/MaxedOut99)** to get:
|
|
@@ -171,4 +153,59 @@ If this helped you out, leave a heart or start a discussion on what should be ad
|
|
| 171 |
- β
Auto installers to skip this repo + All in one workflows (Controlnets, inpainting, upscaling, etc)
|
| 172 |
- β
Free beginner-friendly SDXL ComfyUI workflows (Flux coming soon)
|
| 173 |
- β
Free setup guides
|
| 174 |
-
- β
And so much more coming soon
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
---
|
| 30 |
|
| 31 |
+
# ComfyUI-Starter-Packs
|
| 32 |
+
|
| 33 |
+
A curated vault of essential models for ComfyUI users β organized, curated, and ready.
|
| 34 |
+
No bloat. No hunting through 15 Civitai and Hugging Face repos.
|
| 35 |
+
|
| 36 |
+
---
|
| 37 |
+
### I See You ποΈ
|
| 38 |
+
|
| 39 |
+
Downloads keep rising⦠but with zero new hearts or comments, I have no idea if I'm helping anyone or just feeding a download bot farm in silence.
|
| 40 |
+
If this helped you out, leave a heart or start a discussion on what should be added next. Otherwise Iβll assume I built this for the void (and a very busy botnet).
|
| 41 |
+
|
| 42 |
+
## π¦ Whatβs Inside
|
| 43 |
+
|
| 44 |
+
<details> <summary>π§ Flux1</summary>
|
| 45 |
βββ Flux1
|
| 46 |
β βββ Controlnets
|
| 47 |
β β βββ flux_shakker_labs_union_pro-fp16.safetensors
|
|
|
|
| 91 |
β β βββ ae.safetensors
|
| 92 |
</details>
|
| 93 |
|
| 94 |
+
<details> <summary>π¨ SDXL</summary>
|
|
|
|
|
|
|
|
|
|
| 95 |
βββ SDXL
|
| 96 |
β βββ checkpoints
|
| 97 |
β β βββ Hyper3d.safetensors
|
|
|
|
| 109 |
β β βββ sdxl_vae.safetensors
|
| 110 |
</details>
|
| 111 |
|
| 112 |
+
<details> <summary>π§ ADetailer</summary>
|
|
|
|
|
|
|
| 113 |
βββ Adetailer
|
| 114 |
β βββ Ultralytics
|
| 115 |
β β βββ bbox
|
|
|
|
| 119 |
β β βββ sam_vit_b_01ec64.pth
|
| 120 |
</details>
|
| 121 |
|
| 122 |
+
<details> <summary>π€ Face Restore</summary>
|
|
|
|
|
|
|
| 123 |
βββ FaceRestore_Models
|
| 124 |
β βββ GFPGANv1.4.pth
|
| 125 |
β βββ codeformer.pth
|
| 126 |
</details>
|
| 127 |
|
| 128 |
+
<details> <summary>π Upscale</summary>
|
|
|
|
|
|
|
| 129 |
βββ Upscale_Models
|
| 130 |
β βββ 4x-UltraSharp.pth
|
| 131 |
β βββ RealESRGAN_x2plus.pth
|
| 132 |
</details>
|
| 133 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 134 |
### `Flux/`
|
| 135 |
- UNETs: Dev, Schnell, Depth, Canny, Fill
|
| 136 |
- GGUFs: Q3/Q5/Q6 + FP8
|
|
|
|
| 146 |
|
| 147 |
---
|
| 148 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 149 |
## π Want the Easy Button?
|
| 150 |
|
| 151 |
**[Join Patreon](https://www.patreon.com/MaxedOut99)** to get:
|
|
|
|
| 153 |
- β
Auto installers to skip this repo + All in one workflows (Controlnets, inpainting, upscaling, etc)
|
| 154 |
- β
Free beginner-friendly SDXL ComfyUI workflows (Flux coming soon)
|
| 155 |
- β
Free setup guides
|
| 156 |
+
- β
And so much more coming soon
|
| 157 |
+
|
| 158 |
+
## π Showcase
|
| 159 |
+
|
| 160 |
+
π§ 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 |
+
|
| 164 |
+
|
| 165 |
+

|
| 166 |
+
|
| 167 |
+

|
| 168 |
+
|
| 169 |
+

|
| 170 |
+
|
| 171 |
+
βοΈ Canny:
|
| 172 |
+
|
| 173 |
+
Flux Canny uses an edge map and also lets you prompt freely. Itβs especially good for repurposing parts of an image like the planet in the first example.
|
| 174 |
+
|
| 175 |
+

|
| 176 |
+
|
| 177 |
+

|
| 178 |
+
|
| 179 |
+

|
| 180 |
+
|
| 181 |
+
πΊ OpenPose:
|
| 182 |
+
|
| 183 |
+
Self-explanatory. Itβs great when you donβt want Depth or Canny getting distracted by other elements in the original image.
|
| 184 |
+
|
| 185 |
+

|
| 186 |
+
|
| 187 |
+

|
| 188 |
+
|
| 189 |
+

|
| 190 |
+
|
| 191 |
+
|
| 192 |
+
π« 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. Itβs pretty solid without needing any training, though not perfect. As you can see, it struggled with Aloyβs hair.
|
| 195 |
+
|
| 196 |
+

|
| 197 |
+
|
| 198 |
+

|
| 199 |
+
|
| 200 |
+

|
| 201 |
+
|
| 202 |
+
π Redux
|
| 203 |
+
|
| 204 |
+

|
| 205 |
+
|
| 206 |
+

|
| 207 |
+
|
| 208 |
+

|
| 209 |
+
|
| 210 |
+
Use the style of one image to influence another.
|
| 211 |
+
|