gpt-image-edit

Name: gpt-image-edit
Author: prime-skills

31stars9forks

How to install gpt-image-edit?

prime-skills/runcomfy-agent-skills/gpt-image-edit

$npx -y skills add prime-skills/runcomfy-agent-skills --skill gpt-image-edit

Installs into the current project.

Summary

Edit images with OpenAI GPT Image 2 (the /edit endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation l

Files · 1

View on GitHub

SKILL.md

1	# GPT Image Edit — Pro Pack on RunComfy
2
3	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [Edit endpoint](https://www.runcomfy.com/models/openai/gpt-image-2/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [Text-to-image sibling](https://www.runcomfy.com/models/openai/gpt-image-2/text-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/gpt-image-edit)
4
5	OpenAI GPT Image 2 — `/edit` endpoint (ChatGPT Images 2.0 image-to-image) on the RunComfy Model API. Strongest in its class at preserving identity through targeted edits and rewriting embedded text in any script (Latin, kana, CJK, Cyrillic, Arabic).
6
7	```bash
8	npx skills add agentspace-so/runcomfy-skills --skill gpt-image-edit -g
9	```
10
11	## When to pick this model (vs siblings)
12
13	\| You want \| Use \|
14	\|---\|---\|
15	\| Edit multilingual / embedded text in image \| GPT Image Edit \|
16	\| Identity preservation through translated headline variants \| GPT Image Edit \|
17	\| Layout-precise edit (move headline, swap CTA, etc.) \| GPT Image Edit \|
18	\| Up to 10 reference images \| GPT Image Edit \|
19	\| Batch up to 20 images consistently \| Nano Banana Edit \|
20	\| Single-shot precise local edit, source-fidelity-first \| Flux Kontext \|
21	\| Generate from scratch with GPT Image 2 \| sibling [`gpt-image-2`](../gpt-image-2) skill \|
22	\| Batch SKU galleries with stable identity \| Nano Banana Edit \|
23
24	## Prerequisites
25
26	1. RunComfy CLI — `npm i -g @runcomfy/cli`
27	2. RunComfy account — `runcomfy login` opens a browser device-code flow.
28	3. CI / containers — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`.
29
30	## Endpoints + input schema
31
32	### `openai/gpt-image-2/edit`
33
34	\| Field \| Type \| Required \| Default \| Notes \|
35	\|---\|---\|---\|---\|---\|
36	\| `prompt` \| string \| yes \| — \| Edit instruction. Lead with preservation, end with the change. \|
37	\| `images` \| string[] \| yes \| — \| Up to 10 publicly-fetchable HTTPS URLs. First is primary; rest are auxiliary. \|
38	\| `size` \| enum \| no \| `auto` \| `auto` (preserve input), `1024_1024` (1:1), `1024_1536` (2:3 portrait), `1536_1024` (3:2 landscape). \|
39
40	`size=auto` preserves the input ratio — strongly recommended unless the edit explicitly changes framing.
41
42	## How to invoke
43
44	Single-ref preservation edit:
45
46	```bash
47	runcomfy run openai/gpt-image-2/edit \
48	--input '{
49	"prompt": "Keep the person'\''s face, pose, and brand mark unchanged. Replace the background with a soft warm-grey studio sweep and a gentle floor shadow.",
50	"images": ["https://.../portrait.jpg"]
51	}' \
52	--output-dir <absolute/path>
53	```
54
55	Multilingual text rewrite (preserve everything except the headline):
56
57	```bash
58	runcomfy run openai/gpt-image-2/edit \
59	--input '{
60	"prompt": "Keep the photograph, layout, and brand mark exactly as in the input. Replace only the in-image headline. The new headline reads \"今日のおすすめ\" in bold Japanese kana, same position and font weight as before.",
61	"images": ["https://.../poster-en.jpg"]
62	}' \
63	--output-dir <absolute/path>
64	```
65
66	Multi-ref composition:
67
68	```bash
69	runcomfy run openai/gpt-image-2/edit \
70	--input '{
71	"prompt": "Compose subject from image 1 into the room from image 2. Match the lighting and color palette of image 2. Keep image 1 subject identity (face, pose, clothing) unchanged.",
72	"images": ["https://.../subject.jpg", "https://.../room.jpg"]
73	}' \
74	--output-dir <absolute/path>
75	```
76
77	## Prompting — what actually works
78
79	Lead with preservation goals. Always: `"Keep [face / pose / clothing / brand / framing] unchanged."` Then state the change. The model honors what's stated up front.
80
81	Multilingual text — quote the characters, name the script. `"the headline reads \"コーヒー\" in bold Japanese kana"`, `"the label says \"АРОМА\" in Cyrillic, white on black"`, `"the right-margin caption reads \"تخفيض\" in Arabic right-to-left"`. Don't paraphrase — quote.
82
83	Directional language for spatial edits. Concrete spatial scopes work: `"move the headline from top-right to bottom-center"`, `"remove the

People who liked this also viewed

6 picks

Type

gpt-image-edit

31stars9forks

View on GitHub

How to install gpt-image-edit?

prime-skills/runcomfy-agent-skills/gpt-image-edit

$npx -y skills add prime-skills/runcomfy-agent-skills --skill gpt-image-edit

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# GPT Image Edit — Pro Pack on RunComfy
2
3	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [Edit endpoint](https://www.runcomfy.com/models/openai/gpt-image-2/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [Text-to-image sibling](https://www.runcomfy.com/models/openai/gpt-image-2/text-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/gpt-image-edit)
4
5	OpenAI GPT Image 2 — `/edit` endpoint (ChatGPT Images 2.0 image-to-image) on the RunComfy Model API. Strongest in its class at preserving identity through targeted edits and rewriting embedded text in any script (Latin, kana, CJK, Cyrillic, Arabic).
6
7	```bash
8	npx skills add agentspace-so/runcomfy-skills --skill gpt-image-edit -g
9	```
10
11	## When to pick this model (vs siblings)
12
13	\| You want \| Use \|
14	\|---\|---\|
15	\| Edit multilingual / embedded text in image \| GPT Image Edit \|
16	\| Identity preservation through translated headline variants \| GPT Image Edit \|
17	\| Layout-precise edit (move headline, swap CTA, etc.) \| GPT Image Edit \|
18	\| Up to 10 reference images \| GPT Image Edit \|
19	\| Batch up to 20 images consistently \| Nano Banana Edit \|
20	\| Single-shot precise local edit, source-fidelity-first \| Flux Kontext \|
21	\| Generate from scratch with GPT Image 2 \| sibling [`gpt-image-2`](../gpt-image-2) skill \|
22	\| Batch SKU galleries with stable identity \| Nano Banana Edit \|
23
24	## Prerequisites
25
26	1. RunComfy CLI — `npm i -g @runcomfy/cli`
27	2. RunComfy account — `runcomfy login` opens a browser device-code flow.
28	3. CI / containers — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`.
29
30	## Endpoints + input schema
31
32	### `openai/gpt-image-2/edit`
33
34	\| Field \| Type \| Required \| Default \| Notes \|
35	\|---\|---\|---\|---\|---\|
36	\| `prompt` \| string \| yes \| — \| Edit instruction. Lead with preservation, end with the change. \|
37	\| `images` \| string[] \| yes \| — \| Up to 10 publicly-fetchable HTTPS URLs. First is primary; rest are auxiliary. \|
38	\| `size` \| enum \| no \| `auto` \| `auto` (preserve input), `1024_1024` (1:1), `1024_1536` (2:3 portrait), `1536_1024` (3:2 landscape). \|
39
40	`size=auto` preserves the input ratio — strongly recommended unless the edit explicitly changes framing.
41
42	## How to invoke
43
44	Single-ref preservation edit:
45
46	```bash
47	runcomfy run openai/gpt-image-2/edit \
48	--input '{
49	"prompt": "Keep the person'\''s face, pose, and brand mark unchanged. Replace the background with a soft warm-grey studio sweep and a gentle floor shadow.",
50	"images": ["https://.../portrait.jpg"]
51	}' \
52	--output-dir <absolute/path>
53	```
54
55	Multilingual text rewrite (preserve everything except the headline):
56
57	```bash
58	runcomfy run openai/gpt-image-2/edit \
59	--input '{
60	"prompt": "Keep the photograph, layout, and brand mark exactly as in the input. Replace only the in-image headline. The new headline reads \"今日のおすすめ\" in bold Japanese kana, same position and font weight as before.",
61	"images": ["https://.../poster-en.jpg"]
62	}' \
63	--output-dir <absolute/path>
64	```
65
66	Multi-ref composition:
67
68	```bash
69	runcomfy run openai/gpt-image-2/edit \
70	--input '{
71	"prompt": "Compose subject from image 1 into the room from image 2. Match the lighting and color palette of image 2. Keep image 1 subject identity (face, pose, clothing) unchanged.",
72	"images": ["https://.../subject.jpg", "https://.../room.jpg"]
73	}' \
74	--output-dir <absolute/path>
75	```
76
77	## Prompting — what actually works
78
79	Lead with preservation goals. Always: `"Keep [face / pose / clothing / brand / framing] unchanged."` Then state the change. The model honors what's stated up front.
80
81	Multilingual text — quote the characters, name the script. `"the headline reads \"コーヒー\" in bold Japanese kana"`, `"the label says \"АРОМА\" in Cyrillic, white on black"`, `"the right-margin caption reads \"تخفيض\" in Arabic right-to-left"`. Don't paraphrase — quote.
82
83	Directional language for spatial edits. Concrete spatial scopes work: `"move the headline from top-right to bottom-center"`, `"remove the

People who liked this also viewed

6 picks

Type