Load CLIP

Load Checkpoint

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, static, still

LTXVScheduler

SamplerCustom

KSamplerSelect

LTXVImgToVideo

Load Image

Video Combine 🎥🅥🅗🅢

VAE Decode

Find and Replace

Text Concatenate

replace "photo/image" caption with

Model

Florence2Run

Show Text 🐍

The video is a digital portrait of a young woman with blonde hair styled in loose curls. She is wearing a blue dress with a white collar and a necklace with red berries. The woman is standing on a balcony with a beautiful view of a mountain range in the background. The sky is blue with white clouds and the mountains are covered in snow. The overall mood of the video is peaceful and serene.

String Function 🐍

Image H264 Compression (mtb)

Preview Image

Resize Image

Florence Caption

Upscale

CLIP

text

replace

result_text

replacement_count_number

replacement_count_float

replacement_count_int

value

text_a

text_b

text_c

text_d

STRING

image

florence2_model

mask

caption

data

UPSCALE_MODEL

upscale_model

IMAGE

images

audio

meta_batch

Filenames

OPT_CONNECTION

lora

MASK

get_image_size

width_input

height_input

width

height

clip

CONDITIONING

positive

negative

latent

MODEL

model

sampler

sigmas

latent_image

output

denoised_output

SAMPLER

SIGMAS

samples

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

Apex Artist

with florence caption to auto caption the image

LTX Video Simple

OpenArt

Workflows

Active Sessions

LTX Video Simple

Description

Discussion

Loading...