@miketromba/ploof 0.1.3 → 0.1.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +31 -2
  2. package/SPEC.md +28 -1
  3. package/dist/ploof.js +181 -181
  4. package/package.json +1 -1
package/README.md CHANGED
@@ -9,7 +9,7 @@
9
9
  <img src="https://img.shields.io/badge/node-%3E%3D18-brightgreen" alt="node version" />
10
10
  </p>
11
11
 
12
- Ploof is a CLI for generating and editing creative assets with AI providers. It supports OpenAI image generation and editing today, with a provider registry designed for audio, video, and broader model marketplaces over time.
12
+ Ploof is a CLI for generating and editing creative assets with AI providers. It supports OpenAI image generation, editing, and variations today, with a provider registry designed for audio, video, and broader model marketplaces over time.
13
13
 
14
14
  It is built for both developers and AI agents: predictable commands, parseable output, local auth profiles, YAML manifests, parallel execution, and a companion skill.
15
15
 
@@ -20,6 +20,7 @@ It is built for both developers and AI agents: predictable commands, parseable o
20
20
  | OpenAI auth profiles | Supported |
21
21
  | OpenAI image generation | Supported |
22
22
  | OpenAI image editing | Supported |
23
+ | OpenAI image variations | Supported |
23
24
  | Context images and masks | Supported |
24
25
  | YAML/JSON batch manifests | Supported |
25
26
  | Dependency-aware parallel runs | Supported |
@@ -58,7 +59,6 @@ ploof login openai --api-key <your-api-key>
58
59
  ploof image generate \
59
60
  --prompt "Studio product photo of a matte black water bottle" \
60
61
  --out assets/hero.png \
61
- --model gpt-image-2 \
62
62
  --size 1024x1024
63
63
 
64
64
  # Edit an image with context
@@ -108,6 +108,8 @@ ploof login openai \
108
108
 
109
109
  ## Image Generation
110
110
 
111
+ OpenAI image generation and editing default to `gpt-image-2` when `--model` is omitted.
112
+
111
113
  ```bash
112
114
  ploof image generate \
113
115
  --provider openai \
@@ -150,6 +152,24 @@ ploof image edit \
150
152
 
151
153
  Use repeated `--image` flags for context/reference images. Use `--mask` when the selected provider/model supports masked edits.
152
154
 
155
+ ## Image Variations
156
+
157
+ OpenAI image variations use the legacy variations endpoint and default to `dall-e-2`, which is currently the only supported model for that endpoint.
158
+
159
+ ```bash
160
+ ploof image variation \
161
+ --provider openai \
162
+ --image input.png \
163
+ --out variation.png \
164
+ --size 1024x1024
165
+ ```
166
+
167
+ The plural alias also works:
168
+
169
+ ```bash
170
+ ploof image variations --image input.png --out variation.png
171
+ ```
172
+
153
173
  ## Batch Manifests
154
174
 
155
175
  ```yaml
@@ -176,6 +196,15 @@ tasks:
176
196
  mask: ./mask.png
177
197
  prompt: "Add a premium background"
178
198
  output: assets/final.png
199
+
200
+ - id: variation
201
+ kind: image.variation
202
+ provider: openai
203
+ needs: [base]
204
+ inputs:
205
+ images:
206
+ - task: base
207
+ output: assets/variation.png
179
208
  ```
180
209
 
181
210
  Run it:
package/SPEC.md CHANGED
@@ -86,6 +86,7 @@ Initial capabilities:
86
86
 
87
87
  - `image.generate`
88
88
  - `image.edit`
89
+ - `image.variation`
89
90
 
90
91
  Future providers should be added through the provider registry without changing the manifest model.
91
92
 
@@ -176,6 +177,8 @@ ploof config reset
176
177
 
177
178
  ### Image Generation
178
179
 
180
+ OpenAI image generation and editing default to `gpt-image-2` when no model is specified.
181
+
179
182
  ```bash
180
183
  ploof image generate \
181
184
  --provider openai \
@@ -209,6 +212,20 @@ ploof image edit \
209
212
 
210
213
  The CLI must support multiple context images where the provider supports them.
211
214
 
215
+ ### Image Variations
216
+
217
+ ```bash
218
+ ploof image variation \
219
+ --provider openai \
220
+ --image input.png \
221
+ --out assets/variation.png \
222
+ --model dall-e-2 \
223
+ --size 1024x1024
224
+ ```
225
+
226
+ OpenAI variations default to `dall-e-2`, because the current OpenAI variations
227
+ endpoint only supports that model. `ploof image variations` is an alias.
228
+
212
229
  ### Batch Run
213
230
 
214
231
  ```bash
@@ -241,6 +258,15 @@ tasks:
241
258
  mask: ./mask.png
242
259
  prompt: "Add a premium background"
243
260
  output: assets/final.png
261
+
262
+ - id: variation
263
+ kind: image.variation
264
+ provider: openai
265
+ needs: [base]
266
+ inputs:
267
+ images:
268
+ - task: base
269
+ output: assets/variation.png
244
270
  ```
245
271
 
246
272
  ## Asset Input Model
@@ -280,6 +306,7 @@ type Provider = {
280
306
  capabilities: ProviderCapability[]
281
307
  runImageGenerate(job, context): Promise<ProviderResult>
282
308
  runImageEdit(job, context): Promise<ProviderResult>
309
+ runImageVariation(job, context): Promise<ProviderResult>
283
310
  }
284
311
  ```
285
312
 
@@ -429,7 +456,7 @@ The initial complete implementation should include:
429
456
  - npm package scaffolding for `@miketromba/ploof`.
430
457
  - Build, test, typecheck, lint setup.
431
458
  - OpenAI auth profiles.
432
- - OpenAI image generate/edit.
459
+ - OpenAI image generate/edit/variation.
433
460
  - Asset input normalization.
434
461
  - Manifest run with dependency-aware parallelism.
435
462
  - Output formats and sidecar metadata.