Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ Just a collection of my go-to workflows for Wan 2.2, VACE, and other GGUF video
|
|
16 |
|
17 |
This is stuff that's been tested and actually works. No extra junk nodes, just what you need to get things done. Mostly focused on GGUF and getting decent speed without a 4090.
|
18 |
|
19 |
-
|
20 |
|
21 |
### How To Use
|
22 |
|
@@ -45,47 +45,4 @@ My standard two-pass setup for video-to-video. It uses a high noise model for th
|
|
45 |
|
46 |
---
|
47 |
|
48 |
-
These are just starting points. Tweak the steps, CFG, and LoRA weights to get what you want. Hope it saves you some time.
|
49 |
-
|
50 |
-
---
|
51 |
-
license: apache-2.0
|
52 |
-
language:
|
53 |
-
- en
|
54 |
-
base_model:
|
55 |
-
- Wan-AI/Wan2.2-T2V-A14B
|
56 |
-
- Wan-AI/Wan2.2-I2V-A14B
|
57 |
-
tags:
|
58 |
-
- art
|
59 |
-
---
|
60 |
-
|
61 |
-
# thaakeno's Wan Video Workflows
|
62 |
-
|
63 |
-
Just a collection of my go-to workflows for Wan 2.2, VACE, and other GGUF video models.
|
64 |
-
|
65 |
-
This is stuff that's been tested and actually works. No extra junk nodes, just what you need to get things done. Mostly focused on GGUF and getting decent speed without a 4090.
|
66 |
-
|
67 |
-
### How To Use
|
68 |
-
|
69 |
-
Download the `.json` file you want and just drag it onto your ComfyUI canvas.
|
70 |
-
|
71 |
-
If you get red errors about missing nodes, use the ComfyUI Manager to install them. It's pretty good about finding what's missing.
|
72 |
-
|
73 |
-
You'll obviously need the models, LoRAs, and VAEs too. The filenames are in the loader nodes, so just match them up with what you have.
|
74 |
-
|
75 |
-
### Required Custom Nodes
|
76 |
-
|
77 |
-
You'll need these installed for most of these to work.
|
78 |
-
|
79 |
-
* `ComfyUI-WanVideoWrapper` (Kijai's nodes are the core of most of these)
|
80 |
-
* `ComfyUI-VideoHelperSuite` (for all the VHS stuff, combining, loading)
|
81 |
-
* `comfyui-kjnodes` (lots of useful utilities and reroutes)
|
82 |
-
* A GGUF loader (I use city96's, but others should work)
|
83 |
-
|
84 |
-
### Workflows Included
|
85 |
-
|
86 |
-
**Wan 2.2 - GGUF V2V (2-Pass).json**
|
87 |
-
My standard two-pass setup for video-to-video. It uses a high noise model for the first few steps, then switches to a low noise model to refine and add detail. Good balance of quality and keeping the original motion.
|
88 |
-
|
89 |
-
---
|
90 |
-
|
91 |
-
These are just starting points. Tweak the steps, CFG, and LoRA weights to get what you want. Hope it saves you some time.
|
|
|
16 |
|
17 |
This is stuff that's been tested and actually works. No extra junk nodes, just what you need to get things done. Mostly focused on GGUF and getting decent speed without a 4090.
|
18 |
|
19 |
+
# **[My WAN 2.2 Prompter](https://prompter.on.websim.com/)**
|
20 |
|
21 |
### How To Use
|
22 |
|
|
|
45 |
|
46 |
---
|
47 |
|
48 |
+
These are just starting points. Tweak the steps, CFG, and LoRA weights to get what you want. Hope it saves you some time.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|