--- license: apache-2.0 pipeline_tag: text-to-video language: - en tags: - text-to-image - t2i - wan video - safetensors --- # Workflow for myxx series LoRA
- [myxx Lora](https://huggingface.co/deadman44/WAN_T2i_LoRA)
# Recent - Update some nodes (The quality of kijai nodes seems to have improved): 2025-08-10
- Add this page: 2025-08-04
---

Sample workflow

## - Wan2.2 - [T2i / T2v Workflow](#t2i) - [I2v Workflow](#i2v) - [I2V StartEnd / Random StartEnd Workflow](#startend) - [Highres Upscale Workflow](#highres) - [Speed Mult Workflow](#speedmult) - [Concat Workflow](#concat) - [Reccomended Models](#reccomended) --- ## T2i / T2v - Better Quality Workflow - heavy, but better quality

[Download: T2i/T2v better](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_T2i_better.json)

T2i T2I
15yo, myjc, japanese, photorealistic,
An upper body portrait of a girl in white dress at library.
She has a long black hair with bangs.
She is holding books, and looking at camera.
    
T2v
A girl taking a selfie. The camera circles around the girl.
She has black hair, a ponytail, and is wearing a school uniform.
The background is a daytime classroom with several students.
    

--- ## T2i / T2v (kijai node) - Quality will be lower, but vram fast and saving

[Download: T2i/T2v (kijai)](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_T2i.json)

T2i kijai T2I
T2v
15yo, myjc, japanese, photorealistic, 
portrait of a girl walking at street.
She has a long black ponytail with side bangs.
She is wearing short sleeves school uniform.

--- ## I2v - Better Quality Workflow - heavy, but better quality

[Download: I2v better](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_I2v_better.json)

Start Image I2v better
18yo, myjk, japanese,
A nurse is walking down a dark hospital corridor when suddenly the doctors appear with a bouquet of flowers and she jumps up and down, smiling and overjoyed.
      

### Cut Start Frames - Reduces discomfort at edges, etc. (e.g., collage images) by removing the initial few frames.

Collage Image T2I
Cut the first 4 frames.

--- ## I2V StartEnd Workflow - Start Image -> End Image


[Download: Start_End](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_Start_End.json)

Start Image start
End Image end
18yo, myjk, japanese,
Suddenly A girl in a yellow parachute suit lands with her parachute open on a street crowded with people.
She has a black ponytail with side bangs.
People cheer and applaud.
    
--- ## I2V RandomStartEnd Workflow - Random -> End Image (Not much has changed)


[Download: RandomStart_End](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_RandomStart_End.json)

End Image randomstartend better
18yo, myjk, japanese,
A girl is running.
She wears black twin-tail hair and a school uniform.
In the background is a row of trees and a blue sky, her hair blowing in the wind.
    

## I2v / StartEnd (kijai node) - Quality will be lower, but vram fast and saving

[Download: I2v (kijai)](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_I2v.json)

Collage Image T2I
15yo, myjc, japanese, photorealistic, 
Suddenly few students appear. 
The girl is dancing with students.

--- # Util ## Highres Upscale Workflow - High-resolution upscaling of load images and videos
- image file and movie (webp)
- Low denoise shows less change, high denoise shows more change


[Download: Highres_Upscale](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_Highres_Upscale.json)

Base movie
512 × 768
768 × 1024(1.5x)・denoise: 0.3
--- ## Speed Mult Workflow - Change video speed - webp movie -> mp4

[Download: Speed_Mult](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_Speed_Mult.json)

--- ## Concat MP4 Workflow - Connecting videos - mp4 -> mp4

[Download: Concat_MP4](https://huggingface.co/deadman44/Wan2.2_Workflow_for_myxx_series_LoRA/raw/main/Wan2.2_Concat_MP4.json)

image -> Highres (webp) -> Speed_Mult (mp4) -> Concat (mp4)



--- # Recommended model ### - Wan2.2 Q5, Q4, Q3... will further omit vram
[T2i / T2v]
- [wan2.2_t2v_high_noise_14B_Q8_0.gguf](https://huggingface.co/bullerwins/Wan2.2-T2V-A14B-GGUF/tree/main)
- [wan2.2_t2v_low_noise_14B_Q8_0.gguf](https://huggingface.co/bullerwins/Wan2.2-T2V-A14B-GGUF/tree/main)
[I2v]
- [wan2.2_i2v_high_noise_14B_Q5_K_M.gguf](https://huggingface.co/bullerwins/Wan2.2-I2V-A14B-GGUF/tree/main)
- [wan2.2_i2v_low_noise_14B_Q5_K_M.gguf](https://huggingface.co/bullerwins/Wan2.2-I2V-A14B-GGUF/tree/main)
[etc]
- [umt5_xxl_fp8_e4m3fn_scaled](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)
- [umt5-xxl-enc-bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/umt5-xxl-enc-bf16.safetensors)
- [Wan2_1_VAE_bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_VAE_bf16.safetensors)
[LoRA]
- [Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank128.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v)
- [Wan2.1_T2V_14B_FusionX_LoRA.safetensors](https://huggingface.co/Thelocallab/WAN-2.1-loras/blob/main/Wan2.1_T2V_14B_FusionX_LoRA.safetensors)
- [WAN2.2-LowNoise_SmartphoneSnapshotPhotoReality_v2_by-AI_Characters.safetensors](https://civitai.com/models/1834338?modelVersionId=2075810)
[upscale]
- [4x-ClearRealityV1.pth](https://openmodeldb.info/models/4x-ClearRealityV1)
---