COMFYUI4NOOBS commited on
Commit
7131218
·
verified ·
1 Parent(s): 0815b2d

Add workflows catalog README

Browse files
Files changed (1) hide show
  1. README.md +76 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - comfyui
5
+ - workflow
6
+ - minimax-h3
7
+ - refmod
8
+ ---
9
+
10
+ # Free ComfyUI workflows
11
+
12
+ Public workflows from **COMFYUI 4 NOOBS**. Each JSON in this repo is free to download.
13
+
14
+ Drop a file into ComfyUI, then follow the tutorial linked on that workflow.
15
+
16
+ Community: [COMFYUI 4 NOOBS on Skool](https://www.skool.com/ai-creators-8862/about)
17
+
18
+ ## Workflows
19
+
20
+ | Workflow | File | Tutorial |
21
+ | --- | --- | --- |
22
+ | Create a MiniMax H3 RefMod | [CREATE-REFMOD-WF.json](CREATE-REFMOD-WF.json) | [YouTube Short](https://www.youtube.com/shorts/iL-8mupLCd0) |
23
+
24
+ ## Create a MiniMax H3 RefMod
25
+
26
+ Builds a MiniMax H3 RefMod in ComfyUI from a reference image. The saved graph is set up as an identity RefMod (`Full Reference`, preset `identity_encode`) and writes the result as a bundle.
27
+
28
+ [![How to create a MiniMax H3 RefMod](https://img.youtube.com/vi/iL-8mupLCd0/hqdefault.jpg)](https://www.youtube.com/shorts/iL-8mupLCd0)
29
+
30
+ **Tutorial:** [How to use this workflow](https://www.youtube.com/shorts/iL-8mupLCd0)
31
+
32
+ **File:** [CREATE-REFMOD-WF.json](CREATE-REFMOD-WF.json)
33
+
34
+ **You need:**
35
+
36
+ - ComfyUI with MiniMax H3 support
37
+ - [ComfyUI-MiniMaxH3Mod](https://github.com/Luisacaotica/ComfyUI-MiniMaxH3Mod) (`MiniMaxH3RefModMasterExtract`)
38
+ - [rgthree-comfy](https://github.com/rgthree/rgthree-comfy) (group bypasser and labels)
39
+ - `minimax_h3_video_vae_fp16.safetensors`
40
+ - `minimax_h3_audio_vae_fp32.safetensors` when you turn the audio path on
41
+
42
+ **In this file:**
43
+
44
+ - **Image 1** is the active reference. It feeds `refs_image.ref_image_0`.
45
+ - **Image 2**, **Image 3**, **Image 4**, and the audio loader are in the graph and bypassed. Turn one on when you want another image, a video reference, or a voice.
46
+ - The extract node is named `carlos_mute`, concept `identity`, and **Save** is on with layout `bundle`. Change the name before you run it.
47
+ - The video VAE loader is active. The audio VAE loader is bypassed with the audio input.
48
+
49
+ ## Add the next workflow
50
+
51
+ 1. Upload the new `.json` to the root of this repo.
52
+ 2. Add one row to the table above.
53
+ 3. Copy the block below, fill it in, and paste it above this section.
54
+
55
+ ```markdown
56
+ ## Workflow title
57
+
58
+ One or two sentences on what the workflow does.
59
+
60
+ [![Tutorial](https://img.youtube.com/vi/VIDEO_ID/hqdefault.jpg)](https://www.youtube.com/watch?v=VIDEO_ID)
61
+
62
+ **Tutorial:** [title](https://www.youtube.com/watch?v=VIDEO_ID)
63
+
64
+ **File:** [filename.json](filename.json)
65
+
66
+ **You need:**
67
+
68
+ - ComfyUI
69
+ - custom nodes, with links
70
+ - models this graph expects
71
+
72
+ **In this file:**
73
+
74
+ - Which inputs are active, and which are bypassed.
75
+ - The output name or save settings a user should change.
76
+ ```