Upload 5 files
Browse files- .gitattributes +2 -0
- LTS360BAND.png +3 -0
- Ltx360.json +0 -0
- Ltx360.zip +3 -0
- Ltx360_GUI.png +3 -0
- LtxApp360.txt +42 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
LTS360BAND.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Ltx360_GUI.png filter=lfs diff=lfs merge=lfs -text
|
LTS360BAND.png
ADDED
|
Git LFS Details
|
Ltx360.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Ltx360.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd1d7fcc42dd1bc3dede9406ee0e2fba9b4f42bda6b95e44f0504447b625e410
|
| 3 |
+
size 52820
|
Ltx360_GUI.png
ADDED
|
Git LFS Details
|
LtxApp360.txt
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
|
| 3 |
+
LtxApp360 - i2v/t2v CUSTOM AUDIO DRIVEN 60 SECONDS VIDEO WITH 3 PROMPTS
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
3-Prompts / 60 Seconds Total
|
| 7 |
+
Each prompt = 20 seconds.
|
| 8 |
+
|
| 9 |
+
Using (MANDATORY) a reference audio, This Workflow will lip-sync to the audio you provide.
|
| 10 |
+
For best possible results you should prompt that the subject is talking.
|
| 11 |
+
And if you transcribe what is said in your audio input, results might be even better.
|
| 12 |
+
|
| 13 |
+
My APP MODE Designed for convenience not felxibility, as some of these Workflows if not all from RUNEXX are complex
|
| 14 |
+
for Beginners, and the models he used have to be dug up instead of auto installed with the LTX2.3 template built-in Comfyui
|
| 15 |
+
that most people should start with to get.... Comfy. :)
|
| 16 |
+
|
| 17 |
+
PROMPT EXAMPLE:
|
| 18 |
+
The Punk guitarist sings with perfect lip-sync to the attached audio.
|
| 19 |
+
The viking guitarist on the left plays the main guitar of the attached audio perfect sync.
|
| 20 |
+
The woman drummer in the middle plays the main guitar of the attached audio perfect sync.
|
| 21 |
+
all around the band apocalypse is happening.
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- Replaced the models used by RUNEXX with Official Comfyui LTX2.3 i2v models from the Comfyui template so you don't need
|
| 25 |
+
to look around for models if you just install those from the LTX2.3 i2v comfyui official template.
|
| 26 |
+
- Made a simplified APP Mode for Easy Usage and Beginners.
|
| 27 |
+
- Removed Tael Mini Vae and ltx preview override that are not useful in APP Mode ( also removes the need to go fish for that tiny VAE model )
|
| 28 |
+
- Removed the need/freedom to manually set the width and height.
|
| 29 |
+
- Removed the prompt enhancer for so many reason I can't list here to keep it PG-13.
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
Post-Scriptum:
|
| 33 |
+
I make these workflow for myself and share them here out of my hearts desire.
|
| 34 |
+
Don't ask for support. I already work tech support and you probably can't afford me ;-)
|
| 35 |
+
|
| 36 |
+
This is a very fun APPp
|
| 37 |
+
|
| 38 |
+
OPTIONS:
|
| 39 |
+
- Toggle : t2v / i2v
|
| 40 |
+
- Toggle : High / Low quality
|
| 41 |
+
- Toggle : Custom LoRA OFF/ON ( no Custom LoRA is needed to run this Workflow, I added this option for convenience, note that the LoRA file in the GUI screenshot are there as an example, I do not provide any LoRA.
|
| 42 |
+
|