Update README.md
Browse files
README.md
CHANGED
|
@@ -1,23 +1,22 @@
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
language:
|
| 4 |
-
- en
|
| 5 |
-
base_model:
|
| 6 |
-
- Wan-AI/Wan2.2-T2V-A14B
|
| 7 |
-
- Wan-AI/Wan2.2-I2V-A14B
|
| 8 |
-
tags:
|
| 9 |
-
- art
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
| 13 |
# thaakeno's Wan Video Workflows
|
| 14 |
|
| 15 |
Just a collection of my go-to workflows for Wan 2.2, VACE, and other GGUF video models.
|
| 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 |
|
| 23 |
Download the `.json` file you want and just drag it onto your ComfyUI canvas.
|
|
@@ -30,19 +29,16 @@ You'll obviously need the models, LoRAs, and VAEs too. The filenames are in the
|
|
| 30 |
|
| 31 |
You'll need these installed for most of these to work.
|
| 32 |
|
| 33 |
-
* `ComfyUI-WanVideoWrapper` (Kijai's nodes are the core of most of these)
|
| 34 |
-
* `ComfyUI-VideoHelperSuite` (for all the VHS stuff, combining, loading)
|
| 35 |
-
* `comfyui-kjnodes` (lots of useful utilities and reroutes)
|
| 36 |
-
* A GGUF loader (I use city96's, but others should work)
|
| 37 |
-
|
| 38 |
-
|
| 39 |
|
| 40 |
### Workflows Included
|
| 41 |
|
| 42 |
-
**Wan 2.2 - GGUF V2V (2-Pass).json**
|
| 43 |
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.
|
| 44 |
|
| 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.
|
|
|
|
| 1 |
+
# **[My WAN 2.2 Prompter](https://prompter.on.websim.com/)**
|
| 2 |
+
|
| 3 |
---
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- Wan-AI/Wan2.2-T2V-A14B
|
| 9 |
+
- Wan-AI/Wan2.2-I2V-A14B
|
| 10 |
+
tags:
|
| 11 |
+
- art
|
| 12 |
---
|
| 13 |
|
|
|
|
| 14 |
# thaakeno's Wan Video Workflows
|
| 15 |
|
| 16 |
Just a collection of my go-to workflows for Wan 2.2, VACE, and other GGUF video models.
|
| 17 |
|
| 18 |
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.
|
| 19 |
|
|
|
|
|
|
|
| 20 |
### How To Use
|
| 21 |
|
| 22 |
Download the `.json` file you want and just drag it onto your ComfyUI canvas.
|
|
|
|
| 29 |
|
| 30 |
You'll need these installed for most of these to work.
|
| 31 |
|
| 32 |
+
* `ComfyUI-WanVideoWrapper` (Kijai's nodes are the core of most of these)
|
| 33 |
+
* `ComfyUI-VideoHelperSuite` (for all the VHS stuff, combining, loading)
|
| 34 |
+
* `comfyui-kjnodes` (lots of useful utilities and reroutes)
|
| 35 |
+
* A GGUF loader (I use city96's, but others should work)
|
|
|
|
|
|
|
| 36 |
|
| 37 |
### Workflows Included
|
| 38 |
|
| 39 |
+
**Wan 2.2 - GGUF V2V (2-Pass).json**
|
| 40 |
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.
|
| 41 |
|
|
|
|
| 42 |
---
|
| 43 |
|
| 44 |
+
These are just starting points. Tweak the steps, CFG, and LoRA weights to get what you want. Hope it saves you some time.
|