@huggingface/tasks 0.19.35 → 0.19.37

package/src/tasks/text-generation/data.ts

@@ -63,20 +63,20 @@ const taskData: TaskDataCustom = {
 	models: [
 		{ description: "A text-generation model trained to follow instructions.", id: "google/gemma-2-2b-it" },
 		{
-			description: "Smaller variant of one of the most powerful models.",
-			id: "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+			description: "Powerful text generation model for coding.",
+			id: "Qwen/Qwen3-Coder-480B-A35B-Instruct",
 		},
 		{
-			description: "Very powerful text generation model trained to follow instructions.",
-			id: "meta-llama/Meta-Llama-3.1-8B-Instruct",
+			description: "Great text generation model with top-notch tool calling capabilities.",
+			id: "openai/gpt-oss-120b",
 		},
 		{
-			description: "Powerful text generation model by Microsoft.",
-			id: "microsoft/phi-4",
+			description: "Powerful text generation model.",
+			id: "zai-org/GLM-4.5",
 		},
 		{
-			description: "A very powerful model with reasoning capabilities.",
-			id: "simplescaling/s1.1-32B",
+			description: "A powerful small model with reasoning capabilities.",
+			id: "Qwen/Qwen3-4B-Thinking-2507",
 		},
 		{
 			description: "Strong conversational model that supports very long instructions.",
@@ -93,8 +93,12 @@ const taskData: TaskDataCustom = {
 	],
 	spaces: [
 		{
-			description: "A leaderboard to compare different open-source text generation models based on various benchmarks.",
-			id: "open-llm-leaderboard/open_llm_leaderboard",
+			description: "An application that writes and executes code from text instructions and supports many models.",
+			id: "akhaliq/anycoder",
+		},
+		{
+			description: "An application that builds websites from natural language prompts.",
+			id: "enzostvs/deepsite",
 		},
 		{
 			description: "A leaderboard for comparing chain-of-thought performance of models.",

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

@@ -50,19 +50,19 @@ const taskData: TaskDataCustom = {
 	models: [
 		{
 			description: "One of the most powerful image generation models that can generate realistic outputs.",
-			id: "black-forest-labs/FLUX.1-dev",
+			id: "black-forest-labs/FLUX.1-Krea-dev",
 		},
 		{
-			description: "A powerful yet fast image generation model.",
-			id: "latent-consistency/lcm-lora-sdxl",
+			description: "A powerful image generation model.",
+			id: "Qwen/Qwen-Image",
 		},
 		{
-			description: "Text-to-image model for photorealistic generation.",
-			id: "Kwai-Kolors/Kolors",
+			description: "Powerful and fast image generation model.",
+			id: "ByteDance/SDXL-Lightning",
 		},
 		{
 			description: "A powerful text-to-image model.",
-			id: "stabilityai/stable-diffusion-3-medium-diffusers",
+			id: "ByteDance/Hyper-SD",
 		},
 	],
 	spaces: [

package/src/tasks/text-to-speech/data.ts

@@ -39,24 +39,20 @@ const taskData: TaskDataCustom = {
 	],
 	models: [
 		{
-			description: "A prompt based, powerful TTS model.",
-			id: "parler-tts/parler-tts-large-v1",
+			description: "Small yet powerful TTS model.",
+			id: "KittenML/kitten-tts-nano-0.1",
 		},
 		{
-			description: "A powerful TTS model that supports English and Chinese.",
-			id: "SWivid/F5-TTS",
+			description: "Bleeding edge TTS model.",
+			id: "ResembleAI/chatterbox",
 		},
 		{
 			description: "A massively multi-lingual TTS model.",
 			id: "fishaudio/fish-speech-1.5",
 		},
 		{
-			description: "A powerful TTS model.",
-			id: "OuteAI/OuteTTS-0.1-350M",
-		},
-		{
-			description: "Small yet powerful TTS model.",
-			id: "hexgrad/Kokoro-82M",
+			description: "A text-to-dialogue model.",
+			id: "nari-labs/Dia-1.6B-0626",
 		},
 	],
 	spaces: [
@@ -69,12 +65,12 @@ const taskData: TaskDataCustom = {
 			id: "fishaudio/fish-speech-1",
 		},
 		{
-			description: "An application that generates speech in different styles in English and Chinese.",
-			id: "mrfakename/E2-F5-TTS",
+			description: "Performant TTS application.",
+			id: "ResembleAI/Chatterbox",
 		},
 		{
-			description: "An application that synthesizes emotional speech for diverse speaker prompts.",
-			id: "parler-tts/parler-tts-expresso",
+			description: "An application to compare different TTS models.",
+			id: "TTS-AGI/TTS-Arena-V2",
 		},
 		{
 			description: "An application that generates podcast episodes.",

package/src/tasks/text-to-video/data.ts

@@ -79,8 +79,8 @@ const taskData: TaskDataCustom = {
 			id: "nvidia/Cosmos-1.0-Diffusion-7B-Text2World",
 		},
 		{
-			description: "A robust model for video generation.",
-			id: "Wan-AI/Wan2.1-T2V-1.3B",
+			description: "Very fast model for video generation.",
+			id: "Lightricks/LTX-Video-0.9.8-13B-distilled",
 		},
 	],
 	spaces: [
@@ -99,7 +99,7 @@ const taskData: TaskDataCustom = {
 	],
 	summary:
 		"Text-to-video models can be used in any application that requires generating consistent sequence of images from text. ",
-	widgetModels: ["Wan-AI/Wan2.1-T2V-14B"],
+	widgetModels: ["Wan-AI/Wan2.2-TI2V-5B"],
 	youtubeId: undefined,
 };
 

package/src/tasks/visual-document-retrieval/data.ts

@@ -52,8 +52,9 @@ const taskData: TaskDataCustom = {
 			id: "vidore/colqwen2-v1.0",
 		},
 		{
-			description: "Very fast and efficient visual document retrieval model that works on five languages.",
-			id: "marco/mcdse-2b-v1",
+			description:
+				"Very fast and efficient visual document retrieval model that can also take in other modalities like audio.",
+			id: "Tevatron/OmniEmbed-v0.1",
 		},
 	],
 	spaces: [
@@ -61,6 +62,10 @@ const taskData: TaskDataCustom = {
 			description: "A leaderboard of visual document retrieval models.",
 			id: "vidore/vidore-leaderboard",
 		},
+		{
+			description: "Visual retrieval augmented generation demo based on ColQwen2 model.",
+			id: "vidore/visual-rag-tool",
+		},
 	],
 	summary:
 		"Visual document retrieval is the task of searching for relevant image-based documents, such as PDFs. These models take a text query and multiple documents as input and return the top-most relevant documents and relevancy scores as output.",

package/src/tasks/zero-shot-object-detection/data.ts

@@ -40,17 +40,17 @@ const taskData: TaskDataCustom = {
 	models: [
 		{
 			description: "Solid zero-shot object detection model.",
-			id: "IDEA-Research/grounding-dino-base",
+			id: "openmmlab-community/mm_grounding_dino_large_all",
 		},
 		{
 			description: "Cutting-edge zero-shot object detection model.",
-			id: "google/owlv2-base-patch16-ensemble",
+			id: "fushh7/LLMDet",
 		},
 	],
 	spaces: [
 		{
-			description: "A demo to try the state-of-the-art zero-shot object detection model, OWLv2.",
-			id: "merve/owlv2",
+			description: "A demo to compare different zero-shot object detection models per output and latency.",
+			id: "ariG23498/zero-shot-od",
 		},
 		{
 			description: