Steps

Florence Text (Auto generated)

The video shows a red Volkswagen car driving on a highway at night. The car is in motion, with the headlights on and the taillights on. The road is empty, with no other cars or people visible in the background. The sky is dark, and the road is lined with streetlights on both sides. The streetlights are bright and shining, creating a long exposure effect. In the distance, there are buildings and hills visible. The video is taken from a low angle, looking up at the car and the highway.

Pre Text

After text

Find and Replace

Model

Florence2Run

Text Concatenate

replace "photo/image" caption with

VAE Encode

LTX Attention Override

Modify LTX Model

LTX Apply Perturbed Attention

Add LTX Latent Guide

Resize Image

EmptyLTXVLatentVideo

Final Frame Selector

Preview Image / Last Frame

Extend Video = True

SALT  -   (CRF)

Your own Prompt

Switch to own prompt = TRUE

PEPPER  -  (Frame Rate)

Seed Generator

Dimension (default 768)

Unet Loader (GGUF)

Load VAE

CLIPLoader (GGUF)

Preview Image

🔧 Image From Batch

ImageFromBatch

Animation Builder (mtb)

Load Images (Upload) 🎥🅥🅗🅢

Display Int (rgthree)

CLIP Text Encode (Positive Prompt)

LTXVConditioning

CLIP Text Encode (Negative Prompt)

low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly

LTXVScheduler

SamplerCustom

KSamplerSelect

Load Image Input

Video Combine 🎥🅥🅗🅢

VAE Decode

Select Filename 🎥🅥🅗🅢

Load Video (Path) 🎥🅥🅗🅢

Video Length

LTX/STG

Loader/sampler/misc

Extend: Last Frame current clip

GUI Image to Video with STG and Florence Autocaption  GGUF V6

Make it move       (see note on howto)

Prepare Input Image

Florence Caption

lora

florence2_model

image

seed

mask

caption

data

model

attn_override

MODEL

FLOAT

STRING

images

IMAGE

on_true

on_false

ATTN_OVERRIDE

get_image_size

width_input

height_input

width

height

length

LATENT

latent

image_latent

pixels

steps

SIGMAS

positive

negative

text

replace

result_text

replacement_count_number

replacement_count_float

replacement_count_int

text_a

text_b

text_c

text_d

clip

CONDITIONING

MASK

CLIP

SAMPLER

samples

sampler

sigmas

latent_image

noise_seed

output

denoised_output

Load Image Here

filenames

Filename

audio

meta_batch

frame_rate

Filenames

video

frame_count

video_info

input

batch_index

Press Queue Here
Batch Processing


frame

0-1 (scaled)

count

loop_ended

git+https://github.com/WASasquatch/img2texture.git@d6159abea44a0b2cf77454d3d46962c8b21eb9d3

Apex Artist

automate loading a batch of image folder
youtube tutorial: https://youtu.be/xzY6C8xJJlI

LTX Video Batch Image Folder Automate  Queue

OpenArt

Workflows

Active Sessions

LTX Video Batch Image Folder Automate Queue

Description

Discussion

Loading...