seedance-v2

Name: seedance-v2
Author: prime-skills

31stars9forks

How to install seedance-v2?

prime-skills/runcomfy-agent-skills/seedance-v2

$npx -y skills add prime-skills/runcomfy-agent-skills --skill seedance-v2

Installs into the current project.

Summary

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration

Files · 1

View on GitHub

SKILL.md

1	# Seedance 2.0 Pro — Pro Pack on RunComfy
2
3	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-v2) · [Seedance 2.0 Pro](https://www.runcomfy.com/models/bytedance/seedance-v2/pro?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-v2) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/seedance-v2)
4
5	ByteDance Seedance 2.0 Pro — multimodal cinematic video generator with native lip-synced audio — hosted on the RunComfy Model API.
6
7	```bash
8	npx skills add agentspace-so/runcomfy-skills --skill seedance-v2 -g
9	```
10
11	## When to pick this model (vs siblings)
12
13	Seedance 2.0 Pro's distinct strength is multi-modal cinematic short-form: combine character images + scene videos + reference audio into one coherent shot. Pick it when fidelity to a reference identity / scene matters and you want native lip-sync.
14
15	\| You want \| Use \|
16	\|---\|---\|
17	\| Lip-synced spokesperson / dialogue ad \| Seedance 2.0 Pro \|
18	\| Multi-modal references (image + video + audio) \| Seedance 2.0 Pro \|
19	\| Brand-consistent multi-language narrative \| Seedance 2.0 Pro \|
20	\| Currently-#1 blind-vote video quality \| HappyHorse 1.0 \|
21	\| Audio-driven lip-sync from your own track \| Wan 2.7 (`audio_url`) \|
22	\| Motion editing on existing footage \| Kling Video O1 \|
23	\| Ultra-fast iteration \| LTX 2 \|
24
25	If the user said "Seedance" / "Seedance 2" / "ByteDance video" explicitly, route here regardless.
26
27	## Prerequisites
28
29	1. RunComfy CLI — `npm i -g @runcomfy/cli`
30	2. RunComfy account — `runcomfy login` opens a browser device-code flow.
31	3. CI / containers — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`.
32
33	## Endpoints + input schema
34
35	### `bytedance/seedance-v2/pro`
36
37	\| Field \| Type \| Required \| Default \| Notes \|
38	\|---\|---\|---\|---\|---\|
39	\| `prompt` \| string \| yes \| — \| CN ≤ 500 chars OR EN ≤ 1000 words. \|
40	\| `image_url` \| array \| no \| `[]` \| 0–9 references (JPEG/PNG/WebP/BMP/TIFF/GIF). \|
41	\| `video_url` \| array \| no \| `[]` \| 0–3 clips (MP4/MOV), 2–15s each. \|
42	\| `audio_url` \| array \| no \| `[]` \| 0–3 audio refs (WAV/MP3), 2–15s, < 15MB each. \|
43	\| `aspect_ratio` \| enum \| no \| `adaptive` \| `adaptive`, `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9`. \|
44	\| `duration` \| int \| no \| 5 \| 4–15 (whole seconds). \|
45	\| `resolution` \| enum \| no \| `720p` \| `480p` or `720p`. \|
46	\| `generate_audio` \| bool \| no \| true \| In-pass synchronized speech / SFX / music. \|
47	\| `seed` \| int \| no \| — \| Reproducibility. \|
48
49	## How to invoke
50
51	Default (text only, 5s, 720p with audio):
52
53	```bash
54	runcomfy run bytedance/seedance-v2/pro \
55	--input '{"prompt": "<user prompt>"}' \
56	--output-dir <absolute/path>
57	```
58
59	Lip-synced ad with character reference (image-stable, text-evolves):
60
61	```bash
62	runcomfy run bytedance/seedance-v2/pro \
63	--input '{
64	"prompt": "Medium close-up. The woman explains today'\''s special in a warm friendly tone, slow push-in, soft window light, gentle cafe ambience.",
65	"image_url": ["https://.../barista-headshot.jpg"],
66	"duration": 8,
67	"aspect_ratio": "9:16"
68	}' \
69	--output-dir <absolute/path>
70	```
71
72	Multi-modal (image + video + audio refs):
73
74	```bash
75	runcomfy run bytedance/seedance-v2/pro \
76	--input '{
77	"prompt": "Subject from image 1 walks through the café from video 1, voice tone matches audio 1.",
78	"image_url": ["https://.../subject.jpg"],
79	"video_url": ["https://.../cafe-locked-shot.mp4"],
80	"audio_url": ["https://.../voice-ref.mp3"]
81	}' \
82	--output-dir <absolute/path>
83	```
84
85	The CLI submits, polls, fetches the result, downloads `.runcomfy.net`/`.runcomfy.com` URLs into `--output-dir`.
86
87	## Prompting — what actually works
88
89	Image vs text division. This is the single most important rule. Stable identity (face, costume, brand mark, logo) → put in `image_url`. Evolving narrative (action, mood, lighting, camera) → put in `prompt`. Trying to verbally describe a face in detail wastes tokens and produces drift.
90
91	Camera + motion in plain language. "Medium close-up", "slow push-in", "handheld follow", "locked-off wide" all work as directives. Combine: `"Medium close-up. Slow push-in over 3 seconds. Handheld, slight breathing motion."`
92
93	Audio direction with `generate_audio: true` — say the tone: `"warm friendly conversational"`, `"calm

People who liked this also viewed

6 picks

Type

seedance-v2

31stars9forks

View on GitHub

How to install seedance-v2?

prime-skills/runcomfy-agent-skills/seedance-v2

$npx -y skills add prime-skills/runcomfy-agent-skills --skill seedance-v2

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Seedance 2.0 Pro — Pro Pack on RunComfy
2
3	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-v2) · [Seedance 2.0 Pro](https://www.runcomfy.com/models/bytedance/seedance-v2/pro?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-v2) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/seedance-v2)
4
5	ByteDance Seedance 2.0 Pro — multimodal cinematic video generator with native lip-synced audio — hosted on the RunComfy Model API.
6
7	```bash
8	npx skills add agentspace-so/runcomfy-skills --skill seedance-v2 -g
9	```
10
11	## When to pick this model (vs siblings)
12
13	Seedance 2.0 Pro's distinct strength is multi-modal cinematic short-form: combine character images + scene videos + reference audio into one coherent shot. Pick it when fidelity to a reference identity / scene matters and you want native lip-sync.
14
15	\| You want \| Use \|
16	\|---\|---\|
17	\| Lip-synced spokesperson / dialogue ad \| Seedance 2.0 Pro \|
18	\| Multi-modal references (image + video + audio) \| Seedance 2.0 Pro \|
19	\| Brand-consistent multi-language narrative \| Seedance 2.0 Pro \|
20	\| Currently-#1 blind-vote video quality \| HappyHorse 1.0 \|
21	\| Audio-driven lip-sync from your own track \| Wan 2.7 (`audio_url`) \|
22	\| Motion editing on existing footage \| Kling Video O1 \|
23	\| Ultra-fast iteration \| LTX 2 \|
24
25	If the user said "Seedance" / "Seedance 2" / "ByteDance video" explicitly, route here regardless.
26
27	## Prerequisites
28
29	1. RunComfy CLI — `npm i -g @runcomfy/cli`
30	2. RunComfy account — `runcomfy login` opens a browser device-code flow.
31	3. CI / containers — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`.
32
33	## Endpoints + input schema
34
35	### `bytedance/seedance-v2/pro`
36
37	\| Field \| Type \| Required \| Default \| Notes \|
38	\|---\|---\|---\|---\|---\|
39	\| `prompt` \| string \| yes \| — \| CN ≤ 500 chars OR EN ≤ 1000 words. \|
40	\| `image_url` \| array \| no \| `[]` \| 0–9 references (JPEG/PNG/WebP/BMP/TIFF/GIF). \|
41	\| `video_url` \| array \| no \| `[]` \| 0–3 clips (MP4/MOV), 2–15s each. \|
42	\| `audio_url` \| array \| no \| `[]` \| 0–3 audio refs (WAV/MP3), 2–15s, < 15MB each. \|
43	\| `aspect_ratio` \| enum \| no \| `adaptive` \| `adaptive`, `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9`. \|
44	\| `duration` \| int \| no \| 5 \| 4–15 (whole seconds). \|
45	\| `resolution` \| enum \| no \| `720p` \| `480p` or `720p`. \|
46	\| `generate_audio` \| bool \| no \| true \| In-pass synchronized speech / SFX / music. \|
47	\| `seed` \| int \| no \| — \| Reproducibility. \|
48
49	## How to invoke
50
51	Default (text only, 5s, 720p with audio):
52
53	```bash
54	runcomfy run bytedance/seedance-v2/pro \
55	--input '{"prompt": "<user prompt>"}' \
56	--output-dir <absolute/path>
57	```
58
59	Lip-synced ad with character reference (image-stable, text-evolves):
60
61	```bash
62	runcomfy run bytedance/seedance-v2/pro \
63	--input '{
64	"prompt": "Medium close-up. The woman explains today'\''s special in a warm friendly tone, slow push-in, soft window light, gentle cafe ambience.",
65	"image_url": ["https://.../barista-headshot.jpg"],
66	"duration": 8,
67	"aspect_ratio": "9:16"
68	}' \
69	--output-dir <absolute/path>
70	```
71
72	Multi-modal (image + video + audio refs):
73
74	```bash
75	runcomfy run bytedance/seedance-v2/pro \
76	--input '{
77	"prompt": "Subject from image 1 walks through the café from video 1, voice tone matches audio 1.",
78	"image_url": ["https://.../subject.jpg"],
79	"video_url": ["https://.../cafe-locked-shot.mp4"],
80	"audio_url": ["https://.../voice-ref.mp3"]
81	}' \
82	--output-dir <absolute/path>
83	```
84
85	The CLI submits, polls, fetches the result, downloads `.runcomfy.net`/`.runcomfy.com` URLs into `--output-dir`.
86
87	## Prompting — what actually works
88
89	Image vs text division. This is the single most important rule. Stable identity (face, costume, brand mark, logo) → put in `image_url`. Evolving narrative (action, mood, lighting, camera) → put in `prompt`. Trying to verbally describe a face in detail wastes tokens and produces drift.
90
91	Camera + motion in plain language. "Medium close-up", "slow push-in", "handheld follow", "locked-off wide" all work as directives. Combine: `"Medium close-up. Slow push-in over 3 seconds. Handheld, slight breathing motion."`
92
93	Audio direction with `generate_audio: true` — say the tone: `"warm friendly conversational"`, `"calm

People who liked this also viewed

6 picks

Type