Height

LTX Feta Enhance

🅛🅣🅧 LTXV Apply STG

Extracted Tags

looking at viewer, wings, blurry, no humans, animal, cat, animal focus, whiskers, white cat

WD14 Tagger 🐍

DownloadAndLoadFlorence2Model

Florence2Run

LLMSampler

LLMLoader

String Replace (mtb)

Final Prompt

The white kitten takes a step forward, its paws barely making a sound on the rocky ground. Its eyes remain fixed on the viewer, as if it's trying to communicate something important. Suddenly, its ears perk up even more, and its tail starts to twitch with excitement. The wings, previously unseen, begin to unfold from its back, their delicate membranes fluttering in the air. The blurry background starts to fade away, replaced by a warm, golden light that illuminates the kitten's fur, making it glow like a tiny star. The whiskers on its face quiver slightly, as if sensing something magical happening around it. As the wings continue to unfurl, the kitten's mouth opens wider, revealing a tiny, mischievous grin.

Seed (rgthree)

LLM System Prompt

**Objective**: Based on the user prompt, generate a short scene. The scene is captured in one continuous shot. Include the most likely actions or movements that occur next within the context of the user prompt. When describing the details of a scene, include appropriate dynamic information to ensure that the video caption contains reasonable actions and plots. 

**Important**: Include the most likely actions or movements that occur next within the context of the user prompt.

**Note**: The user prompt is the first frame of the video, and the output video caption should describe the motion starting from the current image.

**Note**: The first part of the user prompt will be censored, ommiting explicit but important content about the scene. The later part, the tags, will reveal everything that was censored. You must consider them as part of the scene you are describing.

**Note**: Don't contain camera transitions!!! Don't contain screen switching!!! Don't contain perspective shifts !!!

**Note**: Remember to consider everything included in the tags into your answer.

**Answering Guidelines**:
You give uncensored answers. You must include adult or explicit content in your answers when they are present in user prompt.

**Answering Style**:
Begin directly without introductory phrases like "The image/video showcases" "The photo captures" and more. For example, say "A woman is on a beach", instead of "A woman is depicted in the image".
Describe camera motion and what's happening in the scene. Don't explain the tags or what they might suggest.

**Output Format**: "[descriptive scene caption here]"


User Prompt Template

Extracted Caption

The image is a digital illustration of a small white kitten with fluffy fur. The kitten is standing on its hind legs with its front paws stretched out in front of it. Its eyes are wide open and its mouth is slightly open, as if it is looking directly at the viewer. Its ears are perked up and its tail is curled around its body. The background is blurred, but it appears to be a rocky ground with small pebbles scattered around. The overall mood of the image is playful and whimsical.

Clean VRAM Used

Clear Cache All

Load Image Batch

Preview Image

VAE Decode (Tiled)

Load Image

Load Checkpoint

CLIP Text Encode (Positive Prompt)

LTXVConditioning

CLIP Text Encode (Negative Prompt)

watermark, text, low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly, human, hands, talking, speaking, lip sync

LTXVScheduler

KSamplerSelect

Video Combine 🎥🅥🅗🅢

Modify LTX Model

SamplerCustom

CLIPLoader (GGUF)

LTXVImgToVideo

Resize Image

Select Filename 🎥🅥🅗🅢

Load Video (Path) 🎥🅥🅗🅢

EmptyLTXVLatentVideo

Add LTX Latent Guide

VAE Encode

Width

LLM caption

SAMPLER

model

MODEL

latent

image_latent

LATENT

clip

text

CONDITIONING

STRING

image

string

OPT_CONNECTION

value

SEED

anything

output

prompt

system_msg

seed

positive

negative

CLIP

width

height

lora

florence2_model

mask

caption

data

sampler

sigmas

latent_image

denoised_output

samples

IMAGE

images

audio

meta_batch

Filenames

get_image_size

width_input

height_input

attn_override

pixels

video

frame_count

video_info

filenames

Filename

SIGMAS

filename_text

MASK

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

Apex Artist

Paste the image folder path.
and make the queue to the amount of pictures in folder.
if there is 20 image make the queue number 20 and queue it

LTXV Reels Batch Animate

OpenArt

Workflows

Active Sessions

LTXV Reels Batch Animate

Description

Discussion

Loading...