ltx2

Name: ltx2
Author: calesthio

41kstars4.9kforks

How to install ltx2?

calesthio/openmontage/ltx2

$npx -y skills add calesthio/OpenMontage --skill ltx2

Installs into the current project.

Summary

AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video cl

Files · 1

View on GitHub

SKILL.md

1	# LTX-2.3 Video Generation
2
3	Generate ~5 second video clips from text prompts or images using the LTX-2.3 22B DiT model.
4	Runs on Modal (A100-80GB). Requires `MODAL_LTX2_ENDPOINT_URL` in `.env`.
5
6	## Quick Reference
7
8	```bash
9	# Text-to-video
10	python3 tools/ltx2.py --prompt "A sunset over the ocean, golden light on waves, cinematic" --output sunset.mp4
11
12	# Image-to-video (animate a still image)
13	python3 tools/ltx2.py --prompt "Gentle camera drift, soft ambient motion" --input photo.jpg --output animated.mp4
14
15	# Custom resolution and duration
16	python3 tools/ltx2.py --prompt "..." --width 1024 --height 576 --num-frames 161 --output wide.mp4
17
18	# Fast mode (fewer steps, quicker)
19	python3 tools/ltx2.py --prompt "..." --quality fast --output quick.mp4
20
21	# Reproducible output
22	python3 tools/ltx2.py --prompt "..." --seed 42 --output reproducible.mp4
23	```
24
25	## Parameters
26
27	\| Parameter \| Default \| Description \|
28	\|-----------\|---------\|-------------\|
29	\| `--prompt` \| (required) \| Text description of the video \|
30	\| `--input` \| - \| Input image for image-to-video \|
31	\| `--width` \| 768 \| Video width (divisible by 64) \|
32	\| `--height` \| 512 \| Video height (divisible by 64) \|
33	\| `--num-frames` \| 121 \| Frame count, must satisfy `(n-1) % 8 == 0` \|
34	\| `--fps` \| 24 \| Frames per second \|
35	\| `--quality` \| standard \| `standard` (30 steps) or `fast` (15 steps) \|
36	\| `--steps` \| 30 \| Override inference steps directly \|
37	\| `--seed` \| random \| Seed for reproducibility \|
38	\| `--output` \| auto \| Output file path \|
39	\| `--negative-prompt` \| sensible default \| What to avoid \|
40
41	## Valid Frame Counts
42
43	`(n - 1) % 8 == 0`: 25 (~1s), 49 (~2s), 73 (~3s), 97 (~4s), 121 (~5s default), 161 (~6.7s), 193 (~8s max practical).
44
45	## Common Resolutions
46
47	\| Resolution \| Ratio \| Notes \|
48	\|------------\|-------\|-------\|
49	\| 768x512 \| 3:2 \| Default, good balance \|
50	\| 512x512 \| 1:1 \| Square, fastest \|
51	\| 1024x576 \| 16:9 \| Widescreen \|
52	\| 576x1024 \| 9:16 \| Portrait/vertical \|
53
54	## Prompting Guide
55
56	LTX-2 responds well to cinematographic descriptions. Layer these dimensions:
57
58	- Camera: "Slow dolly forward", "Aerial drone shot", "Tracking shot", "Static wide angle"
59	- Lighting: "Golden hour", "Cinematic lighting", "Neon-lit", "Soft diffused light"
60	- Motion: "Timelapse of...", "Slow motion", "Gentle camera drift", "Gradually transitions"
61	- Style: "Shot on 35mm film", "Documentary style", "Clean minimal aesthetic"
62	- Negative: Always implicitly avoids "worst quality, blurry, jittery, watermark, text, logo"
63
64	Keep prompts under 200 words. Be specific about the scene.
65
66	### Good Prompts
67
68	```
69	# Atmospheric b-roll
70	"Aerial drone shot slowly flying over turquoise ocean waves breaking on white sand, golden hour sunlight, cinematic"
71
72	# Product/tech scene
73	"Close-up of hands typing on a mechanical keyboard, shallow depth of field, soft desk lamp lighting, cozy atmosphere"
74
75	# Abstract background
76	"Dark moody abstract background with flowing blue light streaks, subtle geometric grid, bokeh particles floating, cinematic tech atmosphere"
77
78	# Animate a portrait
79	"Professional headshot, subtle natural head movement, confident warm expression, studio lighting, shallow depth of field"
80
81	# Animate a slide/screenshot
82	"Gentle subtle particle effects floating across a presentation slide, soft ambient light shifts, very slight camera drift"
83	```
84
85	### Bad Prompts
86
87	```
88	# Too vague
89	"A cool video"
90
91	# Too many competing ideas
92	"A cat riding a skateboard while juggling fire on the moon during a thunderstorm"
93
94	# Describing text/UI (model can't render text reliably)
95	"A website showing the text 'Welcome to our platform'"
96	```
97
98	## Video Production Use Cases
99
100	### B-Roll Clips
101	Generate atmospheric 5s shots for cutaways between narrated scenes:
102	```bash
103	python3 tools/ltx2.py --prompt "Futuristic holographic interface, glowing data visualizations, clean workspace, cinematic" --output broll_tech.mp4
104	python3 tools/ltx2.py --prompt "Aerial view of European city at golden hour, modern architecture" --output broll_europe.mp4
105	```
106
107	### Animated Slide Backgrounds
108	Feed a slide screenshot and add subtle motion:
109	```bash
110	python3 tools/ltx2.py --prompt "Gentle particle effects, soft ambient light shifts, very slight camera drift" --input slide.png --output animated_slide.mp4
111	```
112
113	### Animated Portraits
114	Bring still headshots to life:
115	```bash
116	python3 tools/ltx2.py --prompt "Subtle natural head movement, warm expression, professional lighting" --input headshot.png --output animated_portrait.mp4
117	```
118
119	### Branded Intro/Outro
120	Generate abstract motion backgrounds for title cards:
121	```bash
122	python3 tools/ltx2.py --prompt "Dark moody background with flowing blue and coral light streaks, bokeh particles, cinematic t

People who liked this also viewed

6 picks

Type

ltx2

41kstars4.9kforks

View on GitHub

How to install ltx2?

calesthio/openmontage/ltx2

$npx -y skills add calesthio/OpenMontage --skill ltx2

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LTX-2.3 Video Generation
2
3	Generate ~5 second video clips from text prompts or images using the LTX-2.3 22B DiT model.
4	Runs on Modal (A100-80GB). Requires `MODAL_LTX2_ENDPOINT_URL` in `.env`.
5
6	## Quick Reference
7
8	```bash
9	# Text-to-video
10	python3 tools/ltx2.py --prompt "A sunset over the ocean, golden light on waves, cinematic" --output sunset.mp4
11
12	# Image-to-video (animate a still image)
13	python3 tools/ltx2.py --prompt "Gentle camera drift, soft ambient motion" --input photo.jpg --output animated.mp4
14
15	# Custom resolution and duration
16	python3 tools/ltx2.py --prompt "..." --width 1024 --height 576 --num-frames 161 --output wide.mp4
17
18	# Fast mode (fewer steps, quicker)
19	python3 tools/ltx2.py --prompt "..." --quality fast --output quick.mp4
20
21	# Reproducible output
22	python3 tools/ltx2.py --prompt "..." --seed 42 --output reproducible.mp4
23	```
24
25	## Parameters
26
27	\| Parameter \| Default \| Description \|
28	\|-----------\|---------\|-------------\|
29	\| `--prompt` \| (required) \| Text description of the video \|
30	\| `--input` \| - \| Input image for image-to-video \|
31	\| `--width` \| 768 \| Video width (divisible by 64) \|
32	\| `--height` \| 512 \| Video height (divisible by 64) \|
33	\| `--num-frames` \| 121 \| Frame count, must satisfy `(n-1) % 8 == 0` \|
34	\| `--fps` \| 24 \| Frames per second \|
35	\| `--quality` \| standard \| `standard` (30 steps) or `fast` (15 steps) \|
36	\| `--steps` \| 30 \| Override inference steps directly \|
37	\| `--seed` \| random \| Seed for reproducibility \|
38	\| `--output` \| auto \| Output file path \|
39	\| `--negative-prompt` \| sensible default \| What to avoid \|
40
41	## Valid Frame Counts
42
43	`(n - 1) % 8 == 0`: 25 (~1s), 49 (~2s), 73 (~3s), 97 (~4s), 121 (~5s default), 161 (~6.7s), 193 (~8s max practical).
44
45	## Common Resolutions
46
47	\| Resolution \| Ratio \| Notes \|
48	\|------------\|-------\|-------\|
49	\| 768x512 \| 3:2 \| Default, good balance \|
50	\| 512x512 \| 1:1 \| Square, fastest \|
51	\| 1024x576 \| 16:9 \| Widescreen \|
52	\| 576x1024 \| 9:16 \| Portrait/vertical \|
53
54	## Prompting Guide
55
56	LTX-2 responds well to cinematographic descriptions. Layer these dimensions:
57
58	- Camera: "Slow dolly forward", "Aerial drone shot", "Tracking shot", "Static wide angle"
59	- Lighting: "Golden hour", "Cinematic lighting", "Neon-lit", "Soft diffused light"
60	- Motion: "Timelapse of...", "Slow motion", "Gentle camera drift", "Gradually transitions"
61	- Style: "Shot on 35mm film", "Documentary style", "Clean minimal aesthetic"
62	- Negative: Always implicitly avoids "worst quality, blurry, jittery, watermark, text, logo"
63
64	Keep prompts under 200 words. Be specific about the scene.
65
66	### Good Prompts
67
68	```
69	# Atmospheric b-roll
70	"Aerial drone shot slowly flying over turquoise ocean waves breaking on white sand, golden hour sunlight, cinematic"
71
72	# Product/tech scene
73	"Close-up of hands typing on a mechanical keyboard, shallow depth of field, soft desk lamp lighting, cozy atmosphere"
74
75	# Abstract background
76	"Dark moody abstract background with flowing blue light streaks, subtle geometric grid, bokeh particles floating, cinematic tech atmosphere"
77
78	# Animate a portrait
79	"Professional headshot, subtle natural head movement, confident warm expression, studio lighting, shallow depth of field"
80
81	# Animate a slide/screenshot
82	"Gentle subtle particle effects floating across a presentation slide, soft ambient light shifts, very slight camera drift"
83	```
84
85	### Bad Prompts
86
87	```
88	# Too vague
89	"A cool video"
90
91	# Too many competing ideas
92	"A cat riding a skateboard while juggling fire on the moon during a thunderstorm"
93
94	# Describing text/UI (model can't render text reliably)
95	"A website showing the text 'Welcome to our platform'"
96	```
97
98	## Video Production Use Cases
99
100	### B-Roll Clips
101	Generate atmospheric 5s shots for cutaways between narrated scenes:
102	```bash
103	python3 tools/ltx2.py --prompt "Futuristic holographic interface, glowing data visualizations, clean workspace, cinematic" --output broll_tech.mp4
104	python3 tools/ltx2.py --prompt "Aerial view of European city at golden hour, modern architecture" --output broll_europe.mp4
105	```
106
107	### Animated Slide Backgrounds
108	Feed a slide screenshot and add subtle motion:
109	```bash
110	python3 tools/ltx2.py --prompt "Gentle particle effects, soft ambient light shifts, very slight camera drift" --input slide.png --output animated_slide.mp4
111	```
112
113	### Animated Portraits
114	Bring still headshots to life:
115	```bash
116	python3 tools/ltx2.py --prompt "Subtle natural head movement, warm expression, professional lighting" --input headshot.png --output animated_portrait.mp4
117	```
118
119	### Branded Intro/Outro
120	Generate abstract motion backgrounds for title cards:
121	```bash
122	python3 tools/ltx2.py --prompt "Dark moody background with flowing blue and coral light streaks, bokeh particles, cinematic t

People who liked this also viewed

6 picks

Type