gpt-image

Name: gpt-image
Author: inference-sh

197installs94forks

How to install gpt-image?

inference-sh/skills/gpt-image

$npx -y skills add inference-sh/skills --skill gpt-image

Installs into the current project.

Summary

Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image reference, batch generation. Use for: product mockups, marketing visuals, image editing, concept art

Files · 1

View on GitHub

SKILL.md

1	> Install the belt CLI skill: `npx skills add belt-sh/cli`
2
3	# GPT-Image-2
4
5	Generate and edit images with OpenAI's GPT-Image-2 via [inference.sh](https://inference.sh) CLI.
6
7	## Quick Start
8
9	> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
10
11	```bash
12	belt login
13
14	belt app run openai/gpt-image-2 --input '{"prompt": "a cat astronaut floating in space"}'
15	```
16
17
18	## Capabilities
19
20	GPT-Image-2 supports text-to-image generation, image editing with reference images, and mask-based inpainting — all through a single model.
21
22	\| Feature \| Description \|
23	\|---------\|-------------\|
24	\| Text-to-Image \| Generate images from text prompts \|
25	\| Image Editing \| Edit images using reference images \|
26	\| Inpainting \| Mask-based editing of specific regions \|
27	\| Batch Generation \| Generate up to 10 images at once \|
28	\| Multiple Formats \| PNG, JPEG, WebP output \|
29	\| Flexible Resolution \| Any size in 32px increments (256–4096) \|
30
31	## Examples
32
33	### Text-to-Image
34
35	```bash
36	belt app run openai/gpt-image-2 --input '{
37	"prompt": "professional product photo of sneakers on a white background, studio lighting",
38	"quality": "high"
39	}'
40	```
41
42	### Multiple Images
43
44	```bash
45	belt app run openai/gpt-image-2 --input '{
46	"prompt": "minimalist logo design for a coffee shop",
47	"n": 4,
48	"quality": "medium"
49	}'
50	```
51
52	### Image Editing with Reference
53
54	```bash
55	belt app run openai/gpt-image-2 --input '{
56	"prompt": "change the background to a beach at sunset",
57	"images": ["https://your-image.jpg"]
58	}'
59	```
60
61	### Multi-Image Reference
62
63	```bash
64	belt app run openai/gpt-image-2 --input '{
65	"prompt": "combine these two characters into one scene",
66	"images": ["https://character1.jpg", "https://character2.jpg"]
67	}'
68	```
69
70	### Inpainting with Mask
71
72	```bash
73	belt app run openai/gpt-image-2 --input '{
74	"prompt": "replace with a red sports car",
75	"images": ["https://street-scene.jpg"],
76	"mask": "https://car-mask.png"
77	}'
78	```
79
80	### Custom Resolution
81
82	```bash
83	belt app run openai/gpt-image-2 --input '{
84	"prompt": "wide cinematic landscape, mountains at golden hour",
85	"width": 1920,
86	"height": 1080,
87	"quality": "high"
88	}'
89	```
90
91	### Fast Drafts
92
93	```bash
94	belt app run openai/gpt-image-2 --input '{
95	"prompt": "quick concept sketch of a robot",
96	"quality": "low"
97	}'
98	```
99
100	## Pricing
101
102	\| Quality \| ~Price per Image \|
103	\|---------\|-----------------\|
104	\| Low \| $0.006 \|
105	\| Medium \| $0.024 \|
106	\| High \| $0.21 \|
107
108	Larger resolutions cost more. See `belt app get openai/gpt-image-2` for full pricing details.
109
110	## Parameters
111
112	\| Parameter \| Type \| Default \| Description \|
113	\|-----------\|------\|---------\|-------------\|
114	\| `prompt` \| string \| required \| Text prompt describing the image \|
115	\| `images` \| array \| - \| Reference image(s) for editing \|
116	\| `mask` \| string \| - \| Mask image for inpainting \|
117	\| `n` \| integer \| 1 \| Number of images (1–10) \|
118	\| `quality` \| string \| - \| low, medium, or high \|
119	\| `width` \| integer \| - \| Output width (256–4096, multiples of 32) \|
120	\| `height` \| integer \| - \| Output height (256–4096, multiples of 32) \|
121	\| `output_format` \| string \| png \| png, jpeg, or webp \|
122	\| `output_compression` \| integer \| - \| Compression level for jpeg/webp (0–100) \|
123
124	## Related Skills
125
126	```bash
127	# Full platform skill (all apps)
128	npx skills add inference-sh/skills@infsh-cli
129
130	# All image generation models
131	npx skills add inference-sh/skills@ai-image-generation
132
133	# FLUX models
134	npx skills add inference-sh/skills@flux-image
135
136	# Pruna P-Image (fast & economical)
137	npx skills add inference-sh/skills@p-image
138	```
139
140	Browse all image apps: `belt app store --category image`
141
142	## Documentation
143
144	- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI
145	- [Streaming Results](https://inference.sh/docs/api/sdk/streaming) - Real-time progress updates

People who liked this also viewed

6 picks

Type

gpt-image

197installs94forks

View on GitHub

How to install gpt-image?

inference-sh/skills/gpt-image

$npx -y skills add inference-sh/skills --skill gpt-image

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	> Install the belt CLI skill: `npx skills add belt-sh/cli`
2
3	# GPT-Image-2
4
5	Generate and edit images with OpenAI's GPT-Image-2 via [inference.sh](https://inference.sh) CLI.
6
7	## Quick Start
8
9	> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
10
11	```bash
12	belt login
13
14	belt app run openai/gpt-image-2 --input '{"prompt": "a cat astronaut floating in space"}'
15	```
16
17
18	## Capabilities
19
20	GPT-Image-2 supports text-to-image generation, image editing with reference images, and mask-based inpainting — all through a single model.
21
22	\| Feature \| Description \|
23	\|---------\|-------------\|
24	\| Text-to-Image \| Generate images from text prompts \|
25	\| Image Editing \| Edit images using reference images \|
26	\| Inpainting \| Mask-based editing of specific regions \|
27	\| Batch Generation \| Generate up to 10 images at once \|
28	\| Multiple Formats \| PNG, JPEG, WebP output \|
29	\| Flexible Resolution \| Any size in 32px increments (256–4096) \|
30
31	## Examples
32
33	### Text-to-Image
34
35	```bash
36	belt app run openai/gpt-image-2 --input '{
37	"prompt": "professional product photo of sneakers on a white background, studio lighting",
38	"quality": "high"
39	}'
40	```
41
42	### Multiple Images
43
44	```bash
45	belt app run openai/gpt-image-2 --input '{
46	"prompt": "minimalist logo design for a coffee shop",
47	"n": 4,
48	"quality": "medium"
49	}'
50	```
51
52	### Image Editing with Reference
53
54	```bash
55	belt app run openai/gpt-image-2 --input '{
56	"prompt": "change the background to a beach at sunset",
57	"images": ["https://your-image.jpg"]
58	}'
59	```
60
61	### Multi-Image Reference
62
63	```bash
64	belt app run openai/gpt-image-2 --input '{
65	"prompt": "combine these two characters into one scene",
66	"images": ["https://character1.jpg", "https://character2.jpg"]
67	}'
68	```
69
70	### Inpainting with Mask
71
72	```bash
73	belt app run openai/gpt-image-2 --input '{
74	"prompt": "replace with a red sports car",
75	"images": ["https://street-scene.jpg"],
76	"mask": "https://car-mask.png"
77	}'
78	```
79
80	### Custom Resolution
81
82	```bash
83	belt app run openai/gpt-image-2 --input '{
84	"prompt": "wide cinematic landscape, mountains at golden hour",
85	"width": 1920,
86	"height": 1080,
87	"quality": "high"
88	}'
89	```
90
91	### Fast Drafts
92
93	```bash
94	belt app run openai/gpt-image-2 --input '{
95	"prompt": "quick concept sketch of a robot",
96	"quality": "low"
97	}'
98	```
99
100	## Pricing
101
102	\| Quality \| ~Price per Image \|
103	\|---------\|-----------------\|
104	\| Low \| $0.006 \|
105	\| Medium \| $0.024 \|
106	\| High \| $0.21 \|
107
108	Larger resolutions cost more. See `belt app get openai/gpt-image-2` for full pricing details.
109
110	## Parameters
111
112	\| Parameter \| Type \| Default \| Description \|
113	\|-----------\|------\|---------\|-------------\|
114	\| `prompt` \| string \| required \| Text prompt describing the image \|
115	\| `images` \| array \| - \| Reference image(s) for editing \|
116	\| `mask` \| string \| - \| Mask image for inpainting \|
117	\| `n` \| integer \| 1 \| Number of images (1–10) \|
118	\| `quality` \| string \| - \| low, medium, or high \|
119	\| `width` \| integer \| - \| Output width (256–4096, multiples of 32) \|
120	\| `height` \| integer \| - \| Output height (256–4096, multiples of 32) \|
121	\| `output_format` \| string \| png \| png, jpeg, or webp \|
122	\| `output_compression` \| integer \| - \| Compression level for jpeg/webp (0–100) \|
123
124	## Related Skills
125
126	```bash
127	# Full platform skill (all apps)
128	npx skills add inference-sh/skills@infsh-cli
129
130	# All image generation models
131	npx skills add inference-sh/skills@ai-image-generation
132
133	# FLUX models
134	npx skills add inference-sh/skills@flux-image
135
136	# Pruna P-Image (fast & economical)
137	npx skills add inference-sh/skills@p-image
138	```
139
140	Browse all image apps: `belt app store --category image`
141
142	## Documentation
143
144	- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI
145	- [Streaming Results](https://inference.sh/docs/api/sdk/streaming) - Real-time progress updates

People who liked this also viewed

6 picks

Type