image-inpainting

Name: image-inpainting
Author: prime-skills

31stars9forks

How to install image-inpainting?

prime-skills/runcomfy-agent-skills/image-inpainting

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

Installs into the current project.

Summary

Mask-driven image inpainting on RunComfy via the runcomfy CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro

Files · 1

View on GitHub

SKILL.md

1	# Image Inpainting
2
3	Mask-driven region edits — remove objects, fill gaps, replace masked areas — on RunComfy via the `runcomfy` CLI. This skill routes to Z-Image Turbo Inpainting when a mask is available, and to instruction-driven edit models when the region must be described in prose.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting) · [Z-Image Inpainting](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/inpainting?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting)
6
7	## Powered by the RunComfy CLI
8
9	```bash
10	# 1. Install (see runcomfy-cli skill for details)
11	npm i -g @runcomfy/cli # or: npx -y @runcomfy/cli --version
12
13	# 2. Sign in
14	runcomfy login # or in CI: export RUNCOMFY_TOKEN=<token>
15
16	# 3. Inpaint
17	runcomfy run tongyi-mai/z-image/turbo/inpainting \
18	--input '{"image": "...", "mask_image": "...", "prompt": "..."}' \
19	--output-dir ./out
20	```
21
22	CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill.
23
24	---
25
26	## Pick the right model
27
28	Listed by precision of region targeting (mask-required first, then description-based).
29
30	Z-Image Turbo Inpainting — `tongyi-mai/z-image/turbo/inpainting` (default — mask required)
31	> Dedicated inpainting endpoint with mask, strength, and control-scale. Open-weights, sub-second to a few seconds.
32	> Pick for: precise region edits with a binary mask — object removal, watermark cleanup, full-region replacement.
33	> Avoid for: edits without a mask — use Nano Banana 2 Edit (description-based).
34
35	Z-Image Turbo Inpainting LoRA — [`tongyi-mai/z-image/turbo/inpainting/lora`](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/inpainting/lora?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting)
36	> Inpainting endpoint with LoRA adapter support — apply a fine-tuned style during inpainting.
37	> Pick for: brand-style-locked inpainting (LoRA captures the look, mask defines the region).
38	> Avoid for: generic inpainting — use the base inpainting endpoint.
39
40	Nano Banana 2 Edit — `google/nano-banana-2/edit` (description-based fallback)
41	> Identity-preserving edit driven by spatial language ("the watermark in the bottom-right", "the cables overhead"). No mask required.
42	> Pick for: when no mask is available and the region can be described.
43	> Avoid for: precise pixel-level region edges — use Z-Image Inpainting.
44
45	GPT Image 2 Edit — `openai/gpt-image-2/edit`
46	> Multi-ref edit with layout-precise instructions; honors "remove only the X" directives.
47	> Pick for: complex prompt + reference composition where the masked region needs context from other images.
48	> Avoid for: simple single-image mask-driven jobs — use Z-Image Inpainting.
49
50	FLUX Kontext Pro — `blackforestlabs/flux-1-kontext/pro/edit`
51	> Single-instruction local edit with maximum preservation of everything else.
52	> Pick for: "keep everything except X" style local edits without a mask.
53	> Avoid for: explicit mask-driven workflows — use Z-Image Inpainting.
54
55	---
56
57	## Route 1: Z-Image Turbo Inpainting — default
58
59	Model: `tongyi-mai/z-image/turbo/inpainting`
60	Catalog: [Z-Image inpainting](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/inpainting?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting)
61
62	### Schema
63
64	\| Field \| Type \| Required \| Notes \|
65	\|---\|---\|---\|---\|
66	\| `prompt` \| string \| yes \| What fills the masked region; describe preservation constraints for the surround \|
67	\| `image` \| string \| yes \| Source image URL \|
68	\| `mask_image` \| string \| yes \| Grayscale mask URL (white = inpaint, black = preserve) \|
69	\| `strength` \| float \| no \| 0.3–0.6 for retouching, 0.7–1.0 for full replacement \|
70	\| `control_scale` \| float \| no \| 0.6–0.9 typical \|
71	\| `aspect_ratio` \| enum \| no \| W:H output ratio \|
72	\| `seed` \| int \| no \| Reproducibility \|
73
74	### Invoke
75
76	Object removal (low strength):
77
78	```bash
79	runcomfy run tongy

People who liked this also viewed

6 picks

Type

image-inpainting

31stars9forks

View on GitHub

How to install image-inpainting?

prime-skills/runcomfy-agent-skills/image-inpainting

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Image Inpainting
2
3	Mask-driven region edits — remove objects, fill gaps, replace masked areas — on RunComfy via the `runcomfy` CLI. This skill routes to Z-Image Turbo Inpainting when a mask is available, and to instruction-driven edit models when the region must be described in prose.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting) · [Z-Image Inpainting](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/inpainting?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting)
6
7	## Powered by the RunComfy CLI
8
9	```bash
10	# 1. Install (see runcomfy-cli skill for details)
11	npm i -g @runcomfy/cli # or: npx -y @runcomfy/cli --version
12
13	# 2. Sign in
14	runcomfy login # or in CI: export RUNCOMFY_TOKEN=<token>
15
16	# 3. Inpaint
17	runcomfy run tongyi-mai/z-image/turbo/inpainting \
18	--input '{"image": "...", "mask_image": "...", "prompt": "..."}' \
19	--output-dir ./out
20	```
21
22	CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill.
23
24	---
25
26	## Pick the right model
27
28	Listed by precision of region targeting (mask-required first, then description-based).
29
30	Z-Image Turbo Inpainting — `tongyi-mai/z-image/turbo/inpainting` (default — mask required)
31	> Dedicated inpainting endpoint with mask, strength, and control-scale. Open-weights, sub-second to a few seconds.
32	> Pick for: precise region edits with a binary mask — object removal, watermark cleanup, full-region replacement.
33	> Avoid for: edits without a mask — use Nano Banana 2 Edit (description-based).
34
35	Z-Image Turbo Inpainting LoRA — [`tongyi-mai/z-image/turbo/inpainting/lora`](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/inpainting/lora?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting)
36	> Inpainting endpoint with LoRA adapter support — apply a fine-tuned style during inpainting.
37	> Pick for: brand-style-locked inpainting (LoRA captures the look, mask defines the region).
38	> Avoid for: generic inpainting — use the base inpainting endpoint.
39
40	Nano Banana 2 Edit — `google/nano-banana-2/edit` (description-based fallback)
41	> Identity-preserving edit driven by spatial language ("the watermark in the bottom-right", "the cables overhead"). No mask required.
42	> Pick for: when no mask is available and the region can be described.
43	> Avoid for: precise pixel-level region edges — use Z-Image Inpainting.
44
45	GPT Image 2 Edit — `openai/gpt-image-2/edit`
46	> Multi-ref edit with layout-precise instructions; honors "remove only the X" directives.
47	> Pick for: complex prompt + reference composition where the masked region needs context from other images.
48	> Avoid for: simple single-image mask-driven jobs — use Z-Image Inpainting.
49
50	FLUX Kontext Pro — `blackforestlabs/flux-1-kontext/pro/edit`
51	> Single-instruction local edit with maximum preservation of everything else.
52	> Pick for: "keep everything except X" style local edits without a mask.
53	> Avoid for: explicit mask-driven workflows — use Z-Image Inpainting.
54
55	---
56
57	## Route 1: Z-Image Turbo Inpainting — default
58
59	Model: `tongyi-mai/z-image/turbo/inpainting`
60	Catalog: [Z-Image inpainting](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/inpainting?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-inpainting)
61
62	### Schema
63
64	\| Field \| Type \| Required \| Notes \|
65	\|---\|---\|---\|---\|
66	\| `prompt` \| string \| yes \| What fills the masked region; describe preservation constraints for the surround \|
67	\| `image` \| string \| yes \| Source image URL \|
68	\| `mask_image` \| string \| yes \| Grayscale mask URL (white = inpaint, black = preserve) \|
69	\| `strength` \| float \| no \| 0.3–0.6 for retouching, 0.7–1.0 for full replacement \|
70	\| `control_scale` \| float \| no \| 0.6–0.9 typical \|
71	\| `aspect_ratio` \| enum \| no \| W:H output ratio \|
72	\| `seed` \| int \| no \| Reproducibility \|
73
74	### Invoke
75
76	Object removal (low strength):
77
78	```bash
79	runcomfy run tongy

People who liked this also viewed

6 picks

Type