models/Jib Mix Wan - v2 WAN 2.2 Merge

Jib Mix Wan - v2 WAN 2.2 Merge

|
8/18/2025
|
3:42:16 AM
| Discussion|
0
A gothic-style digital portrait of a young light-skinned woman with freckles, light blue eyes, and messy blonde hair adorned with bright orange and yellow roses, wearing a black choker and dark off-shoulder top against a black background.
Close-up portrait of an elderly woman with silver hair and hazel eyes, wearing pearl earrings, lit with soft Rembrandt-style lighting.
Smiling young woman in orange sporty outfit sitting inside a luxury car, holding a coffee cup with waterfront and city skyline in background during golden hour.
Close-up portrait of a crystal mage woman with ginger hair, blue eyes, wearing a detailed crystal crown and diamond necklace, holding a magical crystal ball with a medieval castle in the background at sunset.

Recommended Prompts

highly detailed

Recommended Negative Prompts

use LightX lora with a negative weight for more realism

(bright:1.2), (overexposed:1.3), (high key:1.2), (blurry:1.2), (out of focus:1.2), (deformed:1.2), (ugly:1.2), (disfigured:1.2), (mutated:1.2), (extra limbs:1.3), (missing limbs:1.3), (bad anatomy:1.3), (malformed hands:1.3), (fewer digits:1.3), (extra digits:1.3), (low quality:1.2), (bad quality:1.2), (poorly drawn:1.2), (render:1.2), (cgi:1.2), (illustration:1.2), (drawing:1.2), (painting:1.2), (sketch:1.2), (cartoon:1.2), (anime:1.2), (watermark:1.2), (text:1.2), (signature:1.2)

Recommended Parameters

samplers

Res_3s, res_3s

steps

2 - 10

cfg

1

Tips

Use the Res_3s sampler with Bong_Tangent scheduler from the RES4LYF custom nodes pack for best results.

Try low steps generation from 2 to 8 steps depending on quality needs.

For more realism, apply LightX lora with a negative weight and increase steps slightly.

Version Highlights

A merge of Wan 2.2 and My V1 mix

Creator Sponsors

Check out the RES4LYF custom nodes pack: https://github.com/ClownsharkBatwing/RES4LYF

Try the free txt2img workflow by AItrepreneur: https://pastebin.com/GPYQjUrx

Support AItrepreneur on Patreon: https://www.patreon.com/c/aitrepreneur/posts

Merge of my favourite Wan image enhancing loras, makes it much faster to use than when adding the lora separately.

Samplers

In my testing/research, I have found the best Sampler is Res_3s with Bong_Tangent Scheduler both from the RES4LYF custom nodes pack: https://github.com/ClownsharkBatwing/RES4LYF

I am using this great free txt2img workflow: https://pastebin.com/GPYQjUrx from AItrepreneur check out his Patreon https://www.patreon.com/c/aitrepreneur/posts

V2 is WAN 2.2. Merge that can do incredibly low steps down to 2 steps.
4 steps look better and 8 steps is great quality.

If you want a bit more realism, you can use the LightX lora with a negative weight, but you might have to then increase steps.




Can make decent images/videos in as low as 6 steps as it has speed loras mixed in.

Contributor

Previous
Babes By Stable Yogi (Pony) - V2+LCM
Next
Evangelion "Post-impact" Apocalyptic Style [Flux.1 D] by AutoPastel - V1

Model Details

Model type

Checkpoint

Base model

Wan Video 14B t2v

Model version

v2 WAN 2.2 Merge

Model hash

2f7ebd4068

Creator

Discussion

Please log in to leave a comment.

Images by Jib Mix Wan - v2 WAN 2.2 Merge

style Images