Phr00t commited on
Commit
bfac579
·
verified ·
1 Parent(s): 73243e3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -7,7 +7,7 @@ tags:
7
  - wan2.2
8
  - accelerator
9
  ---
10
- These are mixtures of WAN 2.2 and other WAN-like models and accelerators (with CLIP and VAE also included) to provide a fast, "all in one" solution for making videos as easily and quickly as possible. FP8 precision.
11
 
12
  **base:** This is the first attempt and very "stable", but mostly WAN 2.1 with few WAN 2.2 features. sa_solver recommended.
13
 
@@ -15,11 +15,13 @@ These are mixtures of WAN 2.2 and other WAN-like models and accelerators (with C
15
 
16
  **V3:** This is a mixture of SkyReels and WAN 2.2, which should improve prompt adherence and quality. euler_a sampler recommended, beta scheduler. Suffers from minor color shifts and noise in I2V, typically just at the start.
17
 
18
- **V4:** WAN 2.2 Lightning in the mix! euler_a/beta recommended. ClipVISION for I2V seems to be very weak due to being dropped in WAN 2.2, so your prompt may need to include more of what should stay in frame. Noise and color shifting generally fixed. WAN 2.1 LORA compatibility issues may be more present in this version.
 
 
19
 
20
  You just need to use the basic ComfyUI "Load Checkpoint" node with these, as you can take the VAE, CLIP and Model all from one AIO safetensors. All models are intended to use 1 CFG and 4 steps. See sampler recommendations for each version.
21
 
22
- v2+ models might be slightly less compatible with WAN 2.1 LORAs, as they bring in more WAN 2.2 features. Adjusting strengths of the LORAs may help (down if you see noise or artifacts). This merge will likely not be compatible with WAN 2.2 "high" LORAs, but should have good compatibility with WAN 2.1 + WAN 2.2 "low" LORAs.
23
 
24
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/631be8402ea8535ea48abbc6/t_SxUFP9oyNz0C8dj6jze.png)
25
 
 
7
  - wan2.2
8
  - accelerator
9
  ---
10
+ These are mixtures of WAN 2.2 and other WAN-like models and accelerators (with CLIP and VAE also included) to provide a fast, "all in one" solution for making videos as easily and quickly as possible. FP8 precision. Start using the latest version available for each type of model (image to video or text to video).
11
 
12
  **base:** This is the first attempt and very "stable", but mostly WAN 2.1 with few WAN 2.2 features. sa_solver recommended.
13
 
 
15
 
16
  **V3:** This is a mixture of SkyReels and WAN 2.2, which should improve prompt adherence and quality. euler_a sampler recommended, beta scheduler. Suffers from minor color shifts and noise in I2V, typically just at the start.
17
 
18
+ **V4:** WAN 2.2 Lightning in the mix! euler_a/beta recommended. I2V noise and color shifting generally fixed, but motion is a bit overexaggerated.
19
+
20
+ **V5:** Improved overexaggeration of I2V model. euler_a/beta recommended.
21
 
22
  You just need to use the basic ComfyUI "Load Checkpoint" node with these, as you can take the VAE, CLIP and Model all from one AIO safetensors. All models are intended to use 1 CFG and 4 steps. See sampler recommendations for each version.
23
 
24
+ WAN 2.1 LORA compatibility is generally still good, along with "low noise" WAN 2.2 LORA compatibility. You might need to adjust LORA strengths (up or down) to get results you want, though.
25
 
26
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/631be8402ea8535ea48abbc6/t_SxUFP9oyNz0C8dj6jze.png)
27