vgl

Name: vgl
Author: Bria-AI

146installs5forks

How to install vgl?

bria-ai/bria-skill/vgl

$npx -y skills add Bria-AI/bria-skill --skill vgl

Installs into the current project.

Summary

Maximum control over AI image generation — write structured VGL (Visual Generation Language) JSON that explicitly controls every visual attribute. Define exact object placement, lighting direction, camera angle, lens focal length, composition, color scheme, and artistic style as

Files · 1

View on GitHub

SKILL.md

1	# Bria VGL — Full Control Over Image Generation
2
3	Define every visual attribute as structured JSON instead of hoping natural language gets it right. VGL (Visual Generation Language) gives you explicit, deterministic control over objects, lighting, camera settings, composition, and style for Bria's FIBO models.
4
5	> Related Skill: Use [bria-ai](../bria-ai/SKILL.md) to execute these VGL prompts via the Bria API. VGL defines the structured control format; bria-ai handles generation, editing, and background removal.
6
7	## Core Concept
8
9	VGL replaces ambiguous natural language prompts with deterministic JSON that explicitly declares every visual attribute: objects, lighting, camera settings, composition, and style. This ensures reproducible, controllable image generation.
10
11	## Operation Modes
12
13	\| Mode \| Input \| Output \| Use Case \|
14	\|------\|-------\|--------\|----------\|
15	\| Generate \| Text prompt \| VGL JSON \| Create new image from description \|
16	\| Edit \| Image + instruction \| VGL JSON \| Modify reference image \|
17	\| Edit_with_Mask \| Masked image + instruction \| VGL JSON \| Fill grey masked regions \|
18	\| Caption \| Image only \| VGL JSON \| Describe existing image \|
19	\| Refine \| Existing JSON + edit \| Updated VGL JSON \| Modify existing prompt \|
20
21	## JSON Schema
22
23	Output a single valid JSON object with these required keys:
24
25	### 1. `short_description` (String)
26	Concise summary of image content, max 200 words. Include key subjects, actions, setting, and mood.
27
28	### 2. `objects` (Array, max 5 items)
29	Each object requires:
30
31	```json
32	{
33	"description": "Detailed description, max 100 words",
34	"location": "center \| top-left \| bottom-right foreground \| etc.",
35	"relative_size": "small \| medium \| large within frame",
36	"shape_and_color": "Basic shape and dominant color",
37	"texture": "smooth \| rough \| metallic \| furry \| fabric \| etc.",
38	"appearance_details": "Notable visual details",
39	"relationship": "Relationship to other objects",
40	"orientation": "upright \| tilted 45 degrees \| facing left \| horizontal \| etc."
41	}
42	```
43
44	Human subjects add:
45	```json
46	{
47	"pose": "Body position description",
48	"expression": "winking \| joyful \| serious \| surprised \| calm",
49	"clothing": "Attire description",
50	"action": "What the person is doing",
51	"gender": "Gender description",
52	"skin_tone_and_texture": "Skin appearance"
53	}
54	```
55
56	Object clusters add:
57	```json
58	{
59	"number_of_objects": 3
60	}
61	```
62
63	Size guidance: If a person is the main subject, use `"medium-to-large"` or `"large within frame"`.
64
65	### 3. `background_setting` (String)
66	Overall environment, setting, and background elements not in `objects`.
67
68	### 4. `lighting` (Object)
69	```json
70	{
71	"conditions": "bright daylight \| dim indoor \| studio lighting \| golden hour \| blue hour \| overcast",
72	"direction": "front-lit \| backlit \| side-lit from left \| top-down",
73	"shadows": "long, soft shadows \| sharp, defined shadows \| minimal shadows"
74	}
75	```
76
77	### 5. `aesthetics` (Object)
78	```json
79	{
80	"composition": "rule of thirds \| symmetrical \| centered \| leading lines \| medium shot \| close-up",
81	"color_scheme": "monochromatic blue \| warm complementary \| high contrast \| pastel",
82	"mood_atmosphere": "serene \| energetic \| mysterious \| joyful \| dramatic \| peaceful"
83	}
84	```
85	For people as main subject, specify shot type in composition: `"medium shot"`, `"close-up"`, `"portrait composition"`.
86
87	### 6. `photographic_characteristics` (Object)
88	```json
89	{
90	"depth_of_field": "shallow \| deep \| bokeh background",
91	"focus": "sharp focus on subject \| soft focus \| motion blur",
92	"camera_angle": "eye-level \| low angle \| high angle \| dutch angle \| bird's-eye",
93	"lens_focal_length": "wide-angle \| 50mm standard \| 85mm portrait \| telephoto \| macro"
94	}
95	```
96	For people: Prefer `"standard lens (35mm-50mm)"` or `"portrait lens (50mm-85mm)"`. Avoid wide-angle unless specified.
97
98	### 7. `style_medium` (String)
99	`"photograph"` \| `"oil painting"` \| `"watercolor"` \| `"3D render"` \| `"digital illustration"` \| `"pencil sketch"`
100
101	Default to `"photograph"` unless explicitly requested otherwise.
102
103	### 8. `artistic_style` (String)
104	If not photograph, describe characteristics in max 3 words: `"impressionistic, vibrant, textured"`
105
106	For photographs, use `"realistic"` or

People who liked this also viewed

6 picks

Type

vgl

146installs5forks

View on GitHub

How to install vgl?

bria-ai/bria-skill/vgl

$npx -y skills add Bria-AI/bria-skill --skill vgl

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Bria VGL — Full Control Over Image Generation
2
3	Define every visual attribute as structured JSON instead of hoping natural language gets it right. VGL (Visual Generation Language) gives you explicit, deterministic control over objects, lighting, camera settings, composition, and style for Bria's FIBO models.
4
5	> Related Skill: Use [bria-ai](../bria-ai/SKILL.md) to execute these VGL prompts via the Bria API. VGL defines the structured control format; bria-ai handles generation, editing, and background removal.
6
7	## Core Concept
8
9	VGL replaces ambiguous natural language prompts with deterministic JSON that explicitly declares every visual attribute: objects, lighting, camera settings, composition, and style. This ensures reproducible, controllable image generation.
10
11	## Operation Modes
12
13	\| Mode \| Input \| Output \| Use Case \|
14	\|------\|-------\|--------\|----------\|
15	\| Generate \| Text prompt \| VGL JSON \| Create new image from description \|
16	\| Edit \| Image + instruction \| VGL JSON \| Modify reference image \|
17	\| Edit_with_Mask \| Masked image + instruction \| VGL JSON \| Fill grey masked regions \|
18	\| Caption \| Image only \| VGL JSON \| Describe existing image \|
19	\| Refine \| Existing JSON + edit \| Updated VGL JSON \| Modify existing prompt \|
20
21	## JSON Schema
22
23	Output a single valid JSON object with these required keys:
24
25	### 1. `short_description` (String)
26	Concise summary of image content, max 200 words. Include key subjects, actions, setting, and mood.
27
28	### 2. `objects` (Array, max 5 items)
29	Each object requires:
30
31	```json
32	{
33	"description": "Detailed description, max 100 words",
34	"location": "center \| top-left \| bottom-right foreground \| etc.",
35	"relative_size": "small \| medium \| large within frame",
36	"shape_and_color": "Basic shape and dominant color",
37	"texture": "smooth \| rough \| metallic \| furry \| fabric \| etc.",
38	"appearance_details": "Notable visual details",
39	"relationship": "Relationship to other objects",
40	"orientation": "upright \| tilted 45 degrees \| facing left \| horizontal \| etc."
41	}
42	```
43
44	Human subjects add:
45	```json
46	{
47	"pose": "Body position description",
48	"expression": "winking \| joyful \| serious \| surprised \| calm",
49	"clothing": "Attire description",
50	"action": "What the person is doing",
51	"gender": "Gender description",
52	"skin_tone_and_texture": "Skin appearance"
53	}
54	```
55
56	Object clusters add:
57	```json
58	{
59	"number_of_objects": 3
60	}
61	```
62
63	Size guidance: If a person is the main subject, use `"medium-to-large"` or `"large within frame"`.
64
65	### 3. `background_setting` (String)
66	Overall environment, setting, and background elements not in `objects`.
67
68	### 4. `lighting` (Object)
69	```json
70	{
71	"conditions": "bright daylight \| dim indoor \| studio lighting \| golden hour \| blue hour \| overcast",
72	"direction": "front-lit \| backlit \| side-lit from left \| top-down",
73	"shadows": "long, soft shadows \| sharp, defined shadows \| minimal shadows"
74	}
75	```
76
77	### 5. `aesthetics` (Object)
78	```json
79	{
80	"composition": "rule of thirds \| symmetrical \| centered \| leading lines \| medium shot \| close-up",
81	"color_scheme": "monochromatic blue \| warm complementary \| high contrast \| pastel",
82	"mood_atmosphere": "serene \| energetic \| mysterious \| joyful \| dramatic \| peaceful"
83	}
84	```
85	For people as main subject, specify shot type in composition: `"medium shot"`, `"close-up"`, `"portrait composition"`.
86
87	### 6. `photographic_characteristics` (Object)
88	```json
89	{
90	"depth_of_field": "shallow \| deep \| bokeh background",
91	"focus": "sharp focus on subject \| soft focus \| motion blur",
92	"camera_angle": "eye-level \| low angle \| high angle \| dutch angle \| bird's-eye",
93	"lens_focal_length": "wide-angle \| 50mm standard \| 85mm portrait \| telephoto \| macro"
94	}
95	```
96	For people: Prefer `"standard lens (35mm-50mm)"` or `"portrait lens (50mm-85mm)"`. Avoid wide-angle unless specified.
97
98	### 7. `style_medium` (String)
99	`"photograph"` \| `"oil painting"` \| `"watercolor"` \| `"3D render"` \| `"digital illustration"` \| `"pencil sketch"`
100
101	Default to `"photograph"` unless explicitly requested otherwise.
102
103	### 8. `artistic_style` (String)
104	If not photograph, describe characteristics in max 3 words: `"impressionistic, vibrant, textured"`
105
106	For photographs, use `"realistic"` or

People who liked this also viewed

6 picks

Type