@huggingface/tasks 0.11.13 → 0.12.0

package/dist/index.cjs

@@ -1406,6 +1406,12 @@ var PIPELINE_DATA = {
     color: "red",
     hideInDatasets: true
   },
+  "any-to-any": {
+    name: "Any-to-Any",
+    modality: "multimodal",
+    color: "yellow",
+    hideInDatasets: true
+  },
   other: {
     name: "Other",
     modality: "other",
@@ -2069,7 +2075,7 @@ var taskData9 = {
       id: "timbrooks/instruct-pix2pix"
     }
   ],
-  summary: "Image-to-image is the task of transforming a source image to match the characteristics of a target image or a target image domain. Any image manipulation and enhancement is possible with image to image models.",
+  summary: "Image-to-image is the task of transforming an input image through a variety of possible manipulations and enhancements, such as super-resolution, image inpainting, colorization, and more.",
   widgetModels: ["lllyasviel/sd-controlnet-canny"],
   youtubeId: ""
 };
@@ -4264,7 +4270,8 @@ var TASKS_MODEL_LIBRARIES = {
   "zero-shot-image-classification": ["transformers", "transformers.js"],
   "zero-shot-object-detection": ["transformers", "transformers.js"],
   "text-to-3d": ["diffusers"],
-  "image-to-3d": ["diffusers"]
+  "image-to-3d": ["diffusers"],
+  "any-to-any": ["transformers"]
 };
 function getData(type, partialTaskData = data_default16) {
   return {
@@ -4275,6 +4282,7 @@ function getData(type, partialTaskData = data_default16) {
   };
 }
 var TASKS_DATA = {
+  "any-to-any": getData("any-to-any", data_default16),
   "audio-classification": getData("audio-classification", data_default),
   "audio-to-audio": getData("audio-to-audio", data_default2),
   "automatic-speech-recognition": getData("automatic-speech-recognition", data_default3),

package/dist/index.js

@@ -1368,6 +1368,12 @@ var PIPELINE_DATA = {
     color: "red",
     hideInDatasets: true
   },
+  "any-to-any": {
+    name: "Any-to-Any",
+    modality: "multimodal",
+    color: "yellow",
+    hideInDatasets: true
+  },
   other: {
     name: "Other",
     modality: "other",
@@ -2031,7 +2037,7 @@ var taskData9 = {
       id: "timbrooks/instruct-pix2pix"
     }
   ],
-  summary: "Image-to-image is the task of transforming a source image to match the characteristics of a target image or a target image domain. Any image manipulation and enhancement is possible with image to image models.",
+  summary: "Image-to-image is the task of transforming an input image through a variety of possible manipulations and enhancements, such as super-resolution, image inpainting, colorization, and more.",
   widgetModels: ["lllyasviel/sd-controlnet-canny"],
   youtubeId: ""
 };
@@ -4226,7 +4232,8 @@ var TASKS_MODEL_LIBRARIES = {
   "zero-shot-image-classification": ["transformers", "transformers.js"],
   "zero-shot-object-detection": ["transformers", "transformers.js"],
   "text-to-3d": ["diffusers"],
-  "image-to-3d": ["diffusers"]
+  "image-to-3d": ["diffusers"],
+  "any-to-any": ["transformers"]
 };
 function getData(type, partialTaskData = data_default16) {
   return {
@@ -4237,6 +4244,7 @@ function getData(type, partialTaskData = data_default16) {
   };
 }
 var TASKS_DATA = {
+  "any-to-any": getData("any-to-any", data_default16),
   "audio-classification": getData("audio-classification", data_default),
   "audio-to-audio": getData("audio-to-audio", data_default2),
   "automatic-speech-recognition": getData("automatic-speech-recognition", data_default3),

package/dist/src/pipelines.d.ts

@@ -403,6 +403,12 @@ export declare const PIPELINE_DATA: {
         color: "red";
         hideInDatasets: true;
     };
+    "any-to-any": {
+        name: string;
+        modality: "multimodal";
+        color: "yellow";
+        hideInDatasets: true;
+    };
     other: {
         name: string;
         modality: "other";
@@ -413,7 +419,7 @@ export declare const PIPELINE_DATA: {
 };
 export type PipelineType = keyof typeof PIPELINE_DATA;
 export type WidgetType = PipelineType | "conversational";
-export declare const PIPELINE_TYPES: ("other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "image-text-to-text" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d" | "image-feature-extraction" | "video-text-to-text" | "keypoint-detection")[];
+export declare const PIPELINE_TYPES: ("other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "image-text-to-text" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d" | "image-feature-extraction" | "video-text-to-text" | "keypoint-detection" | "any-to-any")[];
 export declare const SUBTASK_TYPES: string[];
-export declare const PIPELINE_TYPES_SET: Set<"other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "image-text-to-text" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d" | "image-feature-extraction" | "video-text-to-text" | "keypoint-detection">;
+export declare const PIPELINE_TYPES_SET: Set<"other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "image-text-to-text" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d" | "image-feature-extraction" | "video-text-to-text" | "keypoint-detection" | "any-to-any">;
 //# sourceMappingURL=pipelines.d.ts.map

package/dist/src/pipelines.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"pipelines.d.ts","sourceRoot":"","sources":["../../src/pipelines.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,UAAU,yEAA0E,CAAC;AAElG,MAAM,MAAM,QAAQ,GAAG,CAAC,OAAO,UAAU,CAAC,CAAC,MAAM,CAAC,CAAC;AAEnD,eAAO,MAAM,eAAe;;;;;;;;CAQQ,CAAC;AAErC;;;;;;GAMG;AACH,MAAM,WAAW,OAAO;IACvB;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;CACb;AAED;;;;;GAKG;AACH,MAAM,WAAW,YAAY;IAC5B;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,CAAC,EAAE,OAAO,EAAE,CAAC;IACrB,QAAQ,EAAE,QAAQ,CAAC;IACnB;;OAEG;IACH,KAAK,EAAE,MAAM,GAAG,OAAO,GAAG,QAAQ,GAAG,QAAQ,GAAG,KAAK,GAAG,QAAQ,CAAC;IACjE;;OAEG;IACH,YAAY,CAAC,EAAE,OAAO,CAAC;IACvB;;OAEG;IACH,cAAc,CAAC,EAAE,OAAO,CAAC;CACzB;AAcD,eAAO,MAAM,aAAa;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAgmBc,CAAC;AAEzC,MAAM,MAAM,YAAY,GAAG,MAAM,OAAO,aAAa,CAAC;AAEtD,MAAM,MAAM,UAAU,GAAG,YAAY,GAAG,gBAAgB,CAAC;AAEzD,eAAO,MAAM,cAAc,ioCAA+C,CAAC;AAE3E,eAAO,MAAM,aAAa,UAEN,CAAC;AAErB,eAAO,MAAM,kBAAkB,koCAA0B,CAAC"}
+{"version":3,"file":"pipelines.d.ts","sourceRoot":"","sources":["../../src/pipelines.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,UAAU,yEAA0E,CAAC;AAElG,MAAM,MAAM,QAAQ,GAAG,CAAC,OAAO,UAAU,CAAC,CAAC,MAAM,CAAC,CAAC;AAEnD,eAAO,MAAM,eAAe;;;;;;;;CAQQ,CAAC;AAErC;;;;;;GAMG;AACH,MAAM,WAAW,OAAO;IACvB;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;CACb;AAED;;;;;GAKG;AACH,MAAM,WAAW,YAAY;IAC5B;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,CAAC,EAAE,OAAO,EAAE,CAAC;IACrB,QAAQ,EAAE,QAAQ,CAAC;IACnB;;OAEG;IACH,KAAK,EAAE,MAAM,GAAG,OAAO,GAAG,QAAQ,GAAG,QAAQ,GAAG,KAAK,GAAG,QAAQ,CAAC;IACjE;;OAEG;IACH,YAAY,CAAC,EAAE,OAAO,CAAC;IACvB;;OAEG;IACH,cAAc,CAAC,EAAE,OAAO,CAAC;CACzB;AAcD,eAAO,MAAM,aAAa;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAsmBc,CAAC;AAEzC,MAAM,MAAM,YAAY,GAAG,MAAM,OAAO,aAAa,CAAC;AAEtD,MAAM,MAAM,UAAU,GAAG,YAAY,GAAG,gBAAgB,CAAC;AAEzD,eAAO,MAAM,cAAc,gpCAA+C,CAAC;AAE3E,eAAO,MAAM,aAAa,UAEN,CAAC;AAErB,eAAO,MAAM,kBAAkB,ipCAA0B,CAAC"}

package/dist/src/tasks/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/tasks/index.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AA0CjD,mBAAmB,kCAAkC,CAAC;AACtD,mBAAmB,0CAA0C,CAAC;AAC9D,YAAY,EACX,mBAAmB,EACnB,0BAA0B,EAC1B,oBAAoB,EACpB,4BAA4B,EAC5B,2BAA2B,EAC3B,0BAA0B,EAC1B,gCAAgC,EAChC,+BAA+B,GAC/B,MAAM,6BAA6B,CAAC;AACrC,mBAAmB,yCAAyC,CAAC;AAC7D,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,uBAAuB,CAAC;AAC3C,YAAY,EACX,wBAAwB,EACxB,yBAAyB,EACzB,gCAAgC,EAChC,6BAA6B,GAC7B,MAAM,kCAAkC,CAAC;AAC1C,mBAAmB,4BAA4B,CAAC;AAChD,YAAY,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAC5G,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,8BAA8B,CAAC;AAClD,mBAAmB,8BAA8B,CAAC;AAClD,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,iCAAiC,CAAC;AACrD,mBAAmB,2BAA2B,CAAC;AAC/C,mBAAmB,sCAAsC,CAAC;AAC1D,YAAY,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAC5G,YAAY,EAAE,qBAAqB,EAAE,iBAAiB,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAC;AAC/G,mBAAmB,kCAAkC,CAAC;AACtD,YAAY,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AACnF,YAAY,EACX,6BAA6B,EAC7B,uBAAuB,EACvB,wBAAwB,EACxB,+BAA+B,EAC/B,4BAA4B,GAC5B,MAAM,iCAAiC,CAAC;AACzC,YAAY,EACX,gCAAgC,EAChC,gCAAgC,EAChC,mBAAmB,EACnB,oBAAoB,EACpB,2BAA2B,EAC3B,qCAAqC,EACrC,kCAAkC,EAClC,yBAAyB,EACzB,uCAAuC,EACvC,0BAA0B,GAC1B,MAAM,6BAA6B,CAAC;AACrC,mBAAmB,kCAAkC,CAAC;AACtD,mBAAmB,uCAAuC,CAAC;AAC3D,mBAAmB,sCAAsC,CAAC;AAC1D,mBAAmB,4CAA4C,CAAC;AAChE,YAAY,EACX,WAAW,EACX,4BAA4B,EAC5B,gCAAgC,EAChC,6BAA6B,EAC7B,oCAAoC,GACpC,MAAM,wCAAwC,CAAC;AAEhD,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,oBAAoB,CAAC;AAE1D;;GAEG;AACH,eAAO,MAAM,qBAAqB,EAAE,MAAM,CAAC,YAAY,EAAE,eAAe,EAAE,CA4DzE,CAAC;AAoBF,eAAO,MAAM,UAAU,EAAE,MAAM,CAAC,YAAY,EAAE,QAAQ,GAAG,SAAS,CAoDxD,CAAC;AAEX,MAAM,WAAW,WAAW;IAC3B,WAAW,EAAE,MAAM,CAAC;IACpB,EAAE,EAAE,MAAM,CAAC;CACX;AAED,MAAM,MAAM,aAAa,GACtB;IACA,QAAQ,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,OAAO,CAAC;CACb,GACD;IACA,IAAI,EAAE,KAAK,CAAC;QACX,KAAK,EAAE,MAAM,CAAC;QACd,KAAK,EAAE,MAAM,CAAC;KACd,CAAC,CAAC;IACH,IAAI,EAAE,OAAO,CAAC;CACb,GACD;IACA,QAAQ,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,KAAK,CAAC;CACX,GACD;IACA,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC;IAClB,IAAI,EAAE,SAAS,CAAC;CACf,GACD;IACA,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;CACZ,GACD;IACA,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,KAAK,CAAC;QACb,GAAG,EAAE,MAAM,CAAC;QACZ,KAAK,EAAE,MAAM,CAAC;QACd,IAAI,EAAE,MAAM,CAAC;KACb,CAAC,CAAC;IACH,IAAI,EAAE,kBAAkB,CAAC;CACxB,CAAC;AAEL,MAAM,WAAW,QAAQ;IACxB,MAAM,EAAE,aAAa,EAAE,CAAC;IACxB,OAAO,EAAE,aAAa,EAAE,CAAC;CACzB;AAED,MAAM,WAAW,QAAQ;IACxB,QAAQ,EAAE,WAAW,EAAE,CAAC;IACxB,IAAI,EAAE,QAAQ,CAAC;IACf,EAAE,EAAE,YAAY,CAAC;IACjB,WAAW,CAAC,EAAE,YAAY,CAAC;IAC3B,aAAa,CAAC,EAAE,OAAO,CAAC;IACxB,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,EAAE,eAAe,EAAE,CAAC;IAC7B,OAAO,EAAE,WAAW,EAAE,CAAC;IACvB,MAAM,EAAE,WAAW,EAAE,CAAC;IACtB,MAAM,EAAE,WAAW,EAAE,CAAC;IACtB,OAAO,EAAE,MAAM,CAAC;IAChB,YAAY,EAAE,MAAM,EAAE,CAAC;IACvB,SAAS,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,MAAM,cAAc,GAAG,IAAI,CAAC,QAAQ,EAAE,IAAI,GAAG,OAAO,GAAG,WAAW,CAAC,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/tasks/index.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AA0CjD,mBAAmB,kCAAkC,CAAC;AACtD,mBAAmB,0CAA0C,CAAC;AAC9D,YAAY,EACX,mBAAmB,EACnB,0BAA0B,EAC1B,oBAAoB,EACpB,4BAA4B,EAC5B,2BAA2B,EAC3B,0BAA0B,EAC1B,gCAAgC,EAChC,+BAA+B,GAC/B,MAAM,6BAA6B,CAAC;AACrC,mBAAmB,yCAAyC,CAAC;AAC7D,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,uBAAuB,CAAC;AAC3C,YAAY,EACX,wBAAwB,EACxB,yBAAyB,EACzB,gCAAgC,EAChC,6BAA6B,GAC7B,MAAM,kCAAkC,CAAC;AAC1C,mBAAmB,4BAA4B,CAAC;AAChD,YAAY,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAC5G,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,8BAA8B,CAAC;AAClD,mBAAmB,8BAA8B,CAAC;AAClD,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,iCAAiC,CAAC;AACrD,mBAAmB,2BAA2B,CAAC;AAC/C,mBAAmB,sCAAsC,CAAC;AAC1D,YAAY,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAC5G,YAAY,EAAE,qBAAqB,EAAE,iBAAiB,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAC;AAC/G,mBAAmB,kCAAkC,CAAC;AACtD,YAAY,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AACnF,YAAY,EACX,6BAA6B,EAC7B,uBAAuB,EACvB,wBAAwB,EACxB,+BAA+B,EAC/B,4BAA4B,GAC5B,MAAM,iCAAiC,CAAC;AACzC,YAAY,EACX,gCAAgC,EAChC,gCAAgC,EAChC,mBAAmB,EACnB,oBAAoB,EACpB,2BAA2B,EAC3B,qCAAqC,EACrC,kCAAkC,EAClC,yBAAyB,EACzB,uCAAuC,EACvC,0BAA0B,GAC1B,MAAM,6BAA6B,CAAC;AACrC,mBAAmB,kCAAkC,CAAC;AACtD,mBAAmB,uCAAuC,CAAC;AAC3D,mBAAmB,sCAAsC,CAAC;AAC1D,mBAAmB,4CAA4C,CAAC;AAChE,YAAY,EACX,WAAW,EACX,4BAA4B,EAC5B,gCAAgC,EAChC,6BAA6B,EAC7B,oCAAoC,GACpC,MAAM,wCAAwC,CAAC;AAEhD,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,oBAAoB,CAAC;AAE1D;;GAEG;AACH,eAAO,MAAM,qBAAqB,EAAE,MAAM,CAAC,YAAY,EAAE,eAAe,EAAE,CA6DzE,CAAC;AAoBF,eAAO,MAAM,UAAU,EAAE,MAAM,CAAC,YAAY,EAAE,QAAQ,GAAG,SAAS,CAqDxD,CAAC;AAEX,MAAM,WAAW,WAAW;IAC3B,WAAW,EAAE,MAAM,CAAC;IACpB,EAAE,EAAE,MAAM,CAAC;CACX;AAED,MAAM,MAAM,aAAa,GACtB;IACA,QAAQ,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,OAAO,CAAC;CACb,GACD;IACA,IAAI,EAAE,KAAK,CAAC;QACX,KAAK,EAAE,MAAM,CAAC;QACd,KAAK,EAAE,MAAM,CAAC;KACd,CAAC,CAAC;IACH,IAAI,EAAE,OAAO,CAAC;CACb,GACD;IACA,QAAQ,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,KAAK,CAAC;CACX,GACD;IACA,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC;IAClB,IAAI,EAAE,SAAS,CAAC;CACf,GACD;IACA,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;CACZ,GACD;IACA,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,KAAK,CAAC;QACb,GAAG,EAAE,MAAM,CAAC;QACZ,KAAK,EAAE,MAAM,CAAC;QACd,IAAI,EAAE,MAAM,CAAC;KACb,CAAC,CAAC;IACH,IAAI,EAAE,kBAAkB,CAAC;CACxB,CAAC;AAEL,MAAM,WAAW,QAAQ;IACxB,MAAM,EAAE,aAAa,EAAE,CAAC;IACxB,OAAO,EAAE,aAAa,EAAE,CAAC;CACzB;AAED,MAAM,WAAW,QAAQ;IACxB,QAAQ,EAAE,WAAW,EAAE,CAAC;IACxB,IAAI,EAAE,QAAQ,CAAC;IACf,EAAE,EAAE,YAAY,CAAC;IACjB,WAAW,CAAC,EAAE,YAAY,CAAC;IAC3B,aAAa,CAAC,EAAE,OAAO,CAAC;IACxB,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,EAAE,eAAe,EAAE,CAAC;IAC7B,OAAO,EAAE,WAAW,EAAE,CAAC;IACvB,MAAM,EAAE,WAAW,EAAE,CAAC;IACtB,MAAM,EAAE,WAAW,EAAE,CAAC;IACtB,OAAO,EAAE,MAAM,CAAC;IAChB,YAAY,EAAE,MAAM,EAAE,CAAC;IACvB,SAAS,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,MAAM,cAAc,GAAG,IAAI,CAAC,QAAQ,EAAE,IAAI,GAAG,OAAO,GAAG,WAAW,CAAC,CAAC"}

package/dist/src/tasks/text-to-image/inference.d.ts

@@ -24,8 +24,8 @@ export interface TextToImageInput {
  */
 export interface TextToImageParameters {
     /**
-     * For diffusion models. A higher guidance scale value encourages the model to generate
-     * images closely linked to the text prompt at the expense of lower image quality.
+     * A higher guidance scale value encourages the model to generate images closely linked to
+     * the text prompt, but values too high may cause saturation and other artifacts.
      */
     guidance_scale?: number;
     /**
@@ -33,14 +33,18 @@ export interface TextToImageParameters {
      */
     negative_prompt?: string[];
     /**
-     * For diffusion models. The number of denoising steps. More denoising steps usually lead to
-     * a higher quality image at the expense of slower inference.
+     * The number of denoising steps. More denoising steps usually lead to a higher quality
+     * image at the expense of slower inference.
      */
     num_inference_steps?: number;
     /**
-     * For diffusion models. Override the scheduler with a compatible one
+     * Override the scheduler with a compatible one.
      */
     scheduler?: string;
+    /**
+     * Seed for the random number generator.
+     */
+    seed?: number;
     /**
      * The size in pixel of the output image
      */

package/dist/src/tasks/text-to-image/inference.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-image/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,qBAAqB,CAAC;IACnC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;;;GAIG;AACH,MAAM,WAAW,qBAAqB;IACrC;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;IAC3B;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,WAAW,CAAC,EAAE,UAAU,CAAC;IACzB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-image/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,qBAAqB,CAAC;IACnC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;;;GAIG;AACH,MAAM,WAAW,qBAAqB;IACrC;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;IAC3B;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,IAAI,CAAC,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,WAAW,CAAC,EAAE,UAAU,CAAC;IACzB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AAED;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.11.13",
+  "version": "0.12.0",
   "description": "List of ML tasks for huggingface.co/tasks",
   "repository": "https://github.com/huggingface/huggingface.js.git",
   "publishConfig": {

package/src/pipelines.ts

@@ -670,6 +670,12 @@ export const PIPELINE_DATA = {
 		color: "red",
 		hideInDatasets: true,
 	},
+	"any-to-any": {
+		name: "Any-to-Any",
+		modality: "multimodal",
+		color: "yellow",
+		hideInDatasets: true,
+	},
 	other: {
 		name: "Other",
 		modality: "other",

package/src/tasks/image-to-image/about.md

@@ -1,15 +1,10 @@
-## Use Cases
-
-### Style transfer
+Image-to-image pipelines can also be used in text-to-image tasks, to provide visual guidance to the text-guided generation process.
 
-One of the most popular use cases of image-to-image is style transfer. Style transfer models can convert a normal photography into a painting in the style of a famous painter.
-
-## Task Variants
+## Use Cases
 
 ### Image inpainting
 
-Image inpainting is widely used during photography editing to remove unwanted objects, such as poles, wires, or sensor
-dust.
+Image inpainting is widely used during photography editing to remove unwanted objects, such as poles, wires, or sensor dust.
 
 ### Image colorization
 
@@ -24,18 +19,27 @@ Super-resolution models increase the resolution of an image, allowing for higher
 You can use pipelines for image-to-image in 🧨diffusers library to easily use image-to-image models. See an example for `StableDiffusionImg2ImgPipeline` below.
 
 ```python
-from PIL import Image
-from diffusers import StableDiffusionImg2ImgPipeline
+import torch
+from diffusers import AutoPipelineForImage2Image
+from diffusers.utils import make_image_grid, load_image
 
-model_id_or_path = "runwayml/stable-diffusion-v1-5"
-pipe = StableDiffusionImg2ImgPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16)
-pipe = pipe.to(cuda)
+pipeline = AutoPipelineForImage2Image.from_pretrained(
+    "stabilityai/stable-diffusion-xl-refiner-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+)
 
-init_image = Image.open("mountains_image.jpeg").convert("RGB").resize((768, 512))
-prompt = "A fantasy landscape, trending on artstation"
+# this helps us to reduce memory usage- since SDXL is a bit heavy, this could help by
+# offloading the model to CPU w/o hurting performance.
+pipeline.enable_model_cpu_offload()
 
-images = pipe(prompt=prompt, image=init_image, strength=0.75, guidance_scale=7.5).images
-images[0].save("fantasy_landscape.png")
+# prepare image
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-sdxl-init.png"
+init_image = load_image(url)
+
+prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
+
+# pass prompt and image to pipeline
+image = pipeline(prompt, image=init_image, strength=0.5).images[0]
+make_image_grid([init_image, image], rows=1, cols=2)
 ```
 
 You can use [huggingface.js](https://github.com/huggingface/huggingface.js) to infer image-to-image models on Hugging Face Hub.
@@ -53,13 +57,53 @@ await inference.imageToImage({
 });
 ```
 
-## ControlNet
+## Uses Cases for Text Guided Image Generation
 
-Controlling the outputs of diffusion models only with a text prompt is a challenging problem. ControlNet is a neural network model that provides image-based control to diffusion models. Control images can be edges or other landmarks extracted from a source image.
+### Style Transfer
+
+One of the most popular use cases of image-to-image is style transfer. With style transfer models:
 
-Many ControlNet models were trained in our community event, JAX Diffusers sprint. You can see the full list of the ControlNet models available [here](https://huggingface.co/spaces/jax-diffusers-event/leaderboard).
+- a regular photo can be transformed into a variety of artistic styles or genres, such as a watercolor painting, a comic book illustration and more.
+- new images can be generated using a text prompt, in the style of a reference input image.
+
+See 🧨diffusers example for style transfer with `AutoPipelineForText2Image` below.
+
+```python
+from diffusers import AutoPipelineForText2Image
+from diffusers.utils import load_image
+import torch
+
+# load pipeline
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
+pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
+
+# set the adapter and scales - this is a component that lets us add the style control from an image to the text-to-image model
+scale = {
+    "down": {"block_2": [0.0, 1.0]},
+    "up": {"block_0": [0.0, 1.0, 0.0]},
+}
+pipeline.set_ip_adapter_scale(scale)
+
+style_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg")
+
+generator = torch.Generator(device="cpu").manual_seed(26)
+image = pipeline(
+    prompt="a cat, masterpiece, best quality, high quality",
+    ip_adapter_image=style_image,
+    negative_prompt="text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry",
+    guidance_scale=5,
+    num_inference_steps=30,
+    generator=generator,
+).images[0]
+image
+```
+
+### ControlNet
+
+Controlling the outputs of diffusion models only with a text prompt is a challenging problem. ControlNet is a neural network model that provides image-based control to diffusion models. Control images can be edges or other landmarks extracted from a source image.
+![Examples](https://huggingface.co/datasets/optimum/documentation-images/resolve/main/neuron/models/12-sdxl-text2img-controlnet.png)
 
-## Most Used Model for the Task
+## Pix2Pix
 
 Pix2Pix is a popular model used for image-to-image translation tasks. It is based on a conditional-GAN (generative adversarial network) where instead of a noise vector a 2D image is given as input. More information about Pix2Pix can be retrieved from this [link](https://phillipi.github.io/pix2pix/) where the associated paper and the GitHub repository can be found.
 
@@ -70,8 +114,13 @@ The images below show some examples extracted from the Pix2Pix paper. This model
 ## Useful Resources
 
 - [Image-to-image guide with diffusers](https://huggingface.co/docs/diffusers/using-diffusers/img2img)
+- Image inpainting: [inpainting with 🧨diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/inpaint), [demo](https://huggingface.co/spaces/diffusers/stable-diffusion-xl-inpainting)
+- Colorization: [demo](https://huggingface.co/spaces/modelscope/old_photo_restoration)
+- Super resolution: [image upscaling with 🧨diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/upscale#super-resolution), [demo](https://huggingface.co/spaces/radames/Enhance-This-HiDiffusion-SDXL)
+- [Style transfer and layout control with diffusers 🧨](https://huggingface.co/docs/diffusers/main/en/using-diffusers/ip_adapter#style--layout-control)
 - [Train your ControlNet with diffusers 🧨](https://huggingface.co/blog/train-your-controlnet)
 - [Ultra fast ControlNet with 🧨 Diffusers](https://huggingface.co/blog/controlnet)
+- [List of ControlNets trained in the community JAX Diffusers sprint](https://huggingface.co/spaces/jax-diffusers-event/leaderboard)
 
 ## References
 

package/src/tasks/image-to-image/data.ts

@@ -93,7 +93,7 @@ const taskData: TaskDataCustom = {
 		},
 	],
 	summary:
-		"Image-to-image is the task of transforming a source image to match the characteristics of a target image or a target image domain. Any image manipulation and enhancement is possible with image to image models.",
+		"Image-to-image is the task of transforming an input image through a variety of possible manipulations and enhancements, such as super-resolution, image inpainting, colorization, and more.",
 	widgetModels: ["lllyasviel/sd-controlnet-canny"],
 	youtubeId: "",
 };

package/src/tasks/index.ts

@@ -170,6 +170,7 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
 	"zero-shot-object-detection": ["transformers", "transformers.js"],
 	"text-to-3d": ["diffusers"],
 	"image-to-3d": ["diffusers"],
+	"any-to-any": ["transformers"],
 };
 
 /**
@@ -191,6 +192,7 @@ function getData(type: PipelineType, partialTaskData: TaskDataCustom = placehold
 // Tasks that call getData() without the second argument will
 // have a "placeholder" page.
 export const TASKS_DATA: Record<PipelineType, TaskData | undefined> = {
+	"any-to-any": getData("any-to-any", placeholder),
 	"audio-classification": getData("audio-classification", audioClassification),
 	"audio-to-audio": getData("audio-to-audio", audioToAudio),
 	"automatic-speech-recognition": getData("automatic-speech-recognition", automaticSpeechRecognition),

package/src/tasks/text-to-image/inference.ts

@@ -26,8 +26,8 @@ export interface TextToImageInput {
  */
 export interface TextToImageParameters {
 	/**
-	 * For diffusion models. A higher guidance scale value encourages the model to generate
-	 * images closely linked to the text prompt at the expense of lower image quality.
+	 * A higher guidance scale value encourages the model to generate images closely linked to
+	 * the text prompt, but values too high may cause saturation and other artifacts.
 	 */
 	guidance_scale?: number;
 	/**
@@ -35,14 +35,18 @@ export interface TextToImageParameters {
 	 */
 	negative_prompt?: string[];
 	/**
-	 * For diffusion models. The number of denoising steps. More denoising steps usually lead to
-	 * a higher quality image at the expense of slower inference.
+	 * The number of denoising steps. More denoising steps usually lead to a higher quality
+	 * image at the expense of slower inference.
 	 */
 	num_inference_steps?: number;
 	/**
-	 * For diffusion models. Override the scheduler with a compatible one
+	 * Override the scheduler with a compatible one.
 	 */
 	scheduler?: string;
+	/**
+	 * Seed for the random number generator.
+	 */
+	seed?: number;
 	/**
 	 * The size in pixel of the output image
 	 */

package/src/tasks/text-to-image/spec/input.json

@@ -22,7 +22,7 @@
 			"properties": {
 				"guidance_scale": {
 					"type": "number",
-					"description": "For diffusion models. A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality."
+					"description": "A higher guidance scale value encourages the model to generate images closely linked to the text prompt, but values too high may cause saturation and other artifacts."
 				},
 				"negative_prompt": {
 					"type": "array",
@@ -33,7 +33,7 @@
 				},
 				"num_inference_steps": {
 					"type": "integer",
-					"description": "For diffusion models. The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference."
+					"description": "The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference."
 				},
 				"target_size": {
 					"type": "object",
@@ -50,7 +50,11 @@
 				},
 				"scheduler": {
 					"type": "string",
-					"description": "For diffusion models. Override the scheduler with a compatible one"
+					"description": "Override the scheduler with a compatible one."
+				},
+				"seed": {
+					"type": "integer",
+					"description": "Seed for the random number generator."
 				}
 			}
 		}