nano-banana-2

Name: nano-banana-2
Author: prime-skills

31stars9forks

How to install nano-banana-2?

prime-skills/runcomfy-agent-skills/nano-banana-2

$npx -y skills add prime-skills/runcomfy-agent-skills --skill nano-banana-2

Installs into the current project.

Summary

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iterati

Files · 1

View on GitHub

SKILL.md

1	# Nano Banana 2 — Pro Pack on RunComfy
2
3	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=nano-banana-2) · [Model page](https://www.runcomfy.com/models/google/nano-banana-2?utm_source=skills.sh&utm_medium=skill&utm_campaign=nano-banana-2) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/nano-banana-2)
4
5	Google Nano Banana 2 — the flash-tier text-to-image model in the Gemini family — hosted on the RunComfy Model API. Optimized for ideation, social-thumbnail batches, and rapid drafts with strong in-image typography.
6
7	```bash
8	npx skills add agentspace-so/runcomfy-skills --skill nano-banana-2 -g
9	```
10
11	## When to pick this model (vs siblings)
12
13	Nano Banana 2 is the flash-tier of the Google image-gen line. Pick it when iteration speed and predictable framing matter more than maximum detail.
14
15	\| You want \| Use \|
16	\|---\|---\|
17	\| Rapid drafts, social thumbnails, batch variants \| Nano Banana 2 \|
18	\| In-image typography with predictable rendering \| Nano Banana 2 \|
19	\| Web-grounded image (current events / real entities) \| Nano Banana 2 + `enable_web_search` \|
20	\| Image edit (preserve subject, swap background) \| Nano Banana Edit (sibling skill) \|
21	\| Heavy stylization, painterly look \| Flux 2 \|
22	\| Maximum prompt adherence + multilingual text \| GPT Image 2 \|
23	\| 2K–4K hero shots, max realism \| Seedream 5 \|
24	\| Hyperrealistic portrait \| Nano Banana Pro \|
25
26	If the user said "Nano Banana" / "nano-banana-2" / "Gemini image" explicitly, route here regardless. If they said "Nano Banana" without specifying 2 vs Pro, default to Pro for portraits and 2 for everything else.
27
28	## Prerequisites
29
30	1. RunComfy CLI — `npm i -g @runcomfy/cli`
31	2. RunComfy account — `runcomfy login` opens a browser device-code flow.
32	3. CI / containers — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`.
33
34	## Endpoints + input schema
35
36	### `google/nano-banana-2/text-to-image`
37
38	\| Field \| Type \| Required \| Default \| Notes \|
39	\|---\|---\|---\|---\|---\|
40	\| `prompt` \| string \| yes \| — \| Subject-first description. \|
41	\| `num_images` \| int \| no \| 1 \| 1–4. Use 4 for ideation rounds. \|
42	\| `seed` \| int \| no \| 0 \| Reuse for reproducibility. \|
43	\| `aspect_ratio` \| enum \| no \| `auto` \| `auto`, `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`. \|
44	\| `resolution` \| enum \| no \| `1K` \| `0.5K` (drafts), `1K` (default), `2K` (final), `4K` (max). \|
45	\| `output_format` \| enum \| no \| `png` \| `png`, `jpeg`, `webp`. \|
46	\| `safety_tolerance` \| int \| no \| 4 \| 1 (strict) – 6 (permissive). \|
47	\| `limit_generations` \| bool \| no \| true \| Limit each prompt round to one generation. \|
48	\| `enable_web_search` \| bool \| no \| false \| Adds web grounding (extra cost + latency). \|
49
50	For image edit (preserve subject + apply changes), see the sibling [`nano-banana-edit`](../nano-banana-edit) skill.
51
52	## How to invoke
53
54	Default draft (1K, square, png):
55
56	```bash
57	runcomfy run google/nano-banana-2/text-to-image \
58	--input '{"prompt": "<user prompt>"}' \
59	--output-dir <absolute/path>
60	```
61
62	Vertical 4-up batch for ideation:
63
64	```bash
65	runcomfy run google/nano-banana-2/text-to-image \
66	--input '{
67	"prompt": "<user prompt>",
68	"num_images": 4,
69	"aspect_ratio": "9:16",
70	"resolution": "0.5K"
71	}' \
72	--output-dir <absolute/path>
73	```
74
75	Final at 2K with seed lock:
76
77	```bash
78	runcomfy run google/nano-banana-2/text-to-image \
79	--input '{
80	"prompt": "<user prompt>",
81	"resolution": "2K",
82	"aspect_ratio": "16:9",
83	"seed": 42
84	}' \
85	--output-dir <absolute/path>
86	```
87
88	Web-grounded (current event / real entity):
89
90	```bash
91	runcomfy run google/nano-banana-2/text-to-image \
92	--input '{
93	"prompt": "<prompt referencing a real-world event from this week>",
94	"enable_web_search": true
95	}' \
96	--output-dir <absolute/path>
97	```
98
99	## Prompting — what actually works
100
101	Subject-first declarative grammar. "A cinematic close-up portrait of an American woman standing under neon lights in rainy Tokyo, shallow depth of field, reflective wet streets, ultra-detailed, realistic skin texture" — primary subject, th

People who liked this also viewed

6 picks

Type

nano-banana-2

31stars9forks

View on GitHub

How to install nano-banana-2?

prime-skills/runcomfy-agent-skills/nano-banana-2

$npx -y skills add prime-skills/runcomfy-agent-skills --skill nano-banana-2

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Nano Banana 2 — Pro Pack on RunComfy
2
3	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=nano-banana-2) · [Model page](https://www.runcomfy.com/models/google/nano-banana-2?utm_source=skills.sh&utm_medium=skill&utm_campaign=nano-banana-2) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/nano-banana-2)
4
5	Google Nano Banana 2 — the flash-tier text-to-image model in the Gemini family — hosted on the RunComfy Model API. Optimized for ideation, social-thumbnail batches, and rapid drafts with strong in-image typography.
6
7	```bash
8	npx skills add agentspace-so/runcomfy-skills --skill nano-banana-2 -g
9	```
10
11	## When to pick this model (vs siblings)
12
13	Nano Banana 2 is the flash-tier of the Google image-gen line. Pick it when iteration speed and predictable framing matter more than maximum detail.
14
15	\| You want \| Use \|
16	\|---\|---\|
17	\| Rapid drafts, social thumbnails, batch variants \| Nano Banana 2 \|
18	\| In-image typography with predictable rendering \| Nano Banana 2 \|
19	\| Web-grounded image (current events / real entities) \| Nano Banana 2 + `enable_web_search` \|
20	\| Image edit (preserve subject, swap background) \| Nano Banana Edit (sibling skill) \|
21	\| Heavy stylization, painterly look \| Flux 2 \|
22	\| Maximum prompt adherence + multilingual text \| GPT Image 2 \|
23	\| 2K–4K hero shots, max realism \| Seedream 5 \|
24	\| Hyperrealistic portrait \| Nano Banana Pro \|
25
26	If the user said "Nano Banana" / "nano-banana-2" / "Gemini image" explicitly, route here regardless. If they said "Nano Banana" without specifying 2 vs Pro, default to Pro for portraits and 2 for everything else.
27
28	## Prerequisites
29
30	1. RunComfy CLI — `npm i -g @runcomfy/cli`
31	2. RunComfy account — `runcomfy login` opens a browser device-code flow.
32	3. CI / containers — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`.
33
34	## Endpoints + input schema
35
36	### `google/nano-banana-2/text-to-image`
37
38	\| Field \| Type \| Required \| Default \| Notes \|
39	\|---\|---\|---\|---\|---\|
40	\| `prompt` \| string \| yes \| — \| Subject-first description. \|
41	\| `num_images` \| int \| no \| 1 \| 1–4. Use 4 for ideation rounds. \|
42	\| `seed` \| int \| no \| 0 \| Reuse for reproducibility. \|
43	\| `aspect_ratio` \| enum \| no \| `auto` \| `auto`, `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`. \|
44	\| `resolution` \| enum \| no \| `1K` \| `0.5K` (drafts), `1K` (default), `2K` (final), `4K` (max). \|
45	\| `output_format` \| enum \| no \| `png` \| `png`, `jpeg`, `webp`. \|
46	\| `safety_tolerance` \| int \| no \| 4 \| 1 (strict) – 6 (permissive). \|
47	\| `limit_generations` \| bool \| no \| true \| Limit each prompt round to one generation. \|
48	\| `enable_web_search` \| bool \| no \| false \| Adds web grounding (extra cost + latency). \|
49
50	For image edit (preserve subject + apply changes), see the sibling [`nano-banana-edit`](../nano-banana-edit) skill.
51
52	## How to invoke
53
54	Default draft (1K, square, png):
55
56	```bash
57	runcomfy run google/nano-banana-2/text-to-image \
58	--input '{"prompt": "<user prompt>"}' \
59	--output-dir <absolute/path>
60	```
61
62	Vertical 4-up batch for ideation:
63
64	```bash
65	runcomfy run google/nano-banana-2/text-to-image \
66	--input '{
67	"prompt": "<user prompt>",
68	"num_images": 4,
69	"aspect_ratio": "9:16",
70	"resolution": "0.5K"
71	}' \
72	--output-dir <absolute/path>
73	```
74
75	Final at 2K with seed lock:
76
77	```bash
78	runcomfy run google/nano-banana-2/text-to-image \
79	--input '{
80	"prompt": "<user prompt>",
81	"resolution": "2K",
82	"aspect_ratio": "16:9",
83	"seed": 42
84	}' \
85	--output-dir <absolute/path>
86	```
87
88	Web-grounded (current event / real entity):
89
90	```bash
91	runcomfy run google/nano-banana-2/text-to-image \
92	--input '{
93	"prompt": "<prompt referencing a real-world event from this week>",
94	"enable_web_search": true
95	}' \
96	--output-dir <absolute/path>
97	```
98
99	## Prompting — what actually works
100
101	Subject-first declarative grammar. "A cinematic close-up portrait of an American woman standing under neon lights in rainy Tokyo, shallow depth of field, reflective wet streets, ultra-detailed, realistic skin texture" — primary subject, th

People who liked this also viewed

6 picks

Type