Create one valid .creavax-template.json object for Creavax Template Builder.
Template rules +live model capabilities
Canonical machine-readable Creavax Template Builder context with the current schema, graph rules and live model capabilities for ChatGPT, Claude, Gemini and other AI systems.
How an AI should build a Creavax Template
The context is provider-neutral. Model keys are live catalog references only; portable template model slots must stay capability/requirement based so Creavax can resolve a compatible active model.
Use the live schema in this context as the package authority. Do not invent unsupported fields or input types.
Use the live_models catalog only to understand which capabilities are currently available in Creavax.
Keep template model slots portable and requirement-based. Do not hard-code provider IDs or model_key values inside template.models.
Connect user inputs to Agents, Agents to their Models, optional Agents to downstream Agents, and producing Agents to final Outputs.
Each Model slot/node belongs to exactly one Agent. If multiple Agents need the same capability, create separate Model slots; Creavax may still resolve them to the same real model.
Independent Agents may execute in parallel. Agent -> Agent creates both a data edge and an execution dependency, so downstream Agents wait for all connected upstream Agents; cycles are forbidden.
Never connect a Model directly to an Output.
When a user-facing control changes a real model setting such as video duration, aspect ratio, resolution, FPS, quality or output count, use model.setting_bindings when supported by the schema.
Return valid JSON only when the user asks for the final Creavax template package.
Use the live schema, not assumptions
Schema status: live. Supported input types: text · select · image · video · audio · three_d · file. SEO keywords: maximum 10.
{
"schema_version": "1.0",
"type": "creavax_template",
"template": "{...}"
}163 live model capabilities
Models are loaded from the same public Creavax model catalog used by the product. Use their inputs, outputs, capability buckets and capabilities to design requirements; do not bind the portable template to a catalog key.
Canopy Labs: Orpheus 3B
canopylabs/orpheus-3b-0.1-fttext → audiotext_to_audioCreavax Audio Auto
creavax-audio-autotext → audiotext_to_audioDeepgram: Aura-2
deepgram/aura-2text → audiotext_to_audioDeepgram: Flux TTS (free)
deepgram/flux-tts:freetext → audiotext_to_audioElevenlabs Music v2.5
elevenlabs/music/v2.5text · audio · json → audiotext_to_audioElevenlabs Sound Effects V2
fal-ai/elevenlabs/sound-effects/v2text → audiotext_to_audioElevenlabs Tts Eleven V3
fal-ai/elevenlabs/tts/eleven-v3text → audiotext_to_audioFish Audio: S1
fish-audio/s1text → audiotext_to_audioFish Audio: S2 Pro
fish-audio/s2-protext → audiotext_to_audioFish Audio: S2.1 Pro Free (free)
fish-audio/s2.1-pro-free:freetext → audiotext_to_audioGoogle: Gemini 3.1 Flash TTS Preview
google/gemini-3.1-flash-tts-previewtext → audiotext_to_audioGoogle: Lyria 3 Clip Preview
google/lyria-3-clip-previewtext · image → audio · texttext_to_audio · image_to_audioGoogle: Lyria 3 Pro Preview
google/lyria-3-pro-previewtext · image → audio · texttext_to_audio · image_to_audiohexgrad: Kokoro 82M
hexgrad/kokoro-82mtext → audiotext_to_audioMicrosoft AI: MAI-Voice-2
microsoft/mai-voice-2text → audiotext_to_audioMicrosoft AI: MAI-Voice-2-Flash
microsoft/mai-voice-2-flashtext → audiotext_to_audioMiniMax: Speech 2.8 HD
minimax/speech-2.8-hdtext → audiotext_to_audioMiniMax: Speech 2.8 Turbo
minimax/speech-2.8-turbotext → audiotext_to_audioOpenAI: GPT Audio
openai/gpt-audiotext · audio → audio · texttext_to_audio · audio_to_audioOpenAI: GPT Audio Mini
openai/gpt-audio-minitext · audio → audio · texttext_to_audio · audio_to_audioQwen: Qwen-Audio-3.0-TTS Flash
qwen/qwen-audio-3.0-tts-flashtext → audiotext_to_audioQwen: Qwen-Audio-3.0-TTS Plus
qwen/qwen-audio-3.0-tts-plustext → audiotext_to_audioSesame: CSM 1B
sesame/csm-1btext → audiotext_to_audioSpaceXAI: Grok Voice TTS 1.0
x-ai/grok-voice-tts-1.0text → audiotext_to_audioAuraSR
fal-ai/aura-srimage → imageimage_upscaleBlack Forest Labs: FLUX.2 Flex
black-forest-labs/flux.2-flextext · image → imagetext_to_image · image_to_imageBlack Forest Labs: FLUX.2 Max
black-forest-labs/flux.2-maxtext · image → imagetext_to_image · image_to_imageBlack Forest Labs: FLUX.2 Pro
black-forest-labs/flux.2-protext · image → imagetext_to_image · image_to_imageBria Increase Resolution: Upscale Images up to 4x Without Losing Detail | fal
bria/increase-resolutionimage → imageimage_upscaleByteDance Seed: Seedream 4.5
bytedance-seed/seedream-4.5text · image → imagetext_to_image · image_to_imageByteDance Seed: Seedream 5.0 Lite
bytedance-seed/seedream-5-0-litetext · image → imagetext_to_image · image_to_imageByteDance Seed: Seedream 5.0 Pro
bytedance-seed/seedream-5-0-protext · image → imagetext_to_image · image_to_imageCCSR Upscaler
fal-ai/ccsrimage → imageimage_upscaleChrono Edit
fal-ai/chrono-edittext · image → imageimage_to_imageClarity Upscaler
fal-ai/clarity-upscalertext · image → imageimage_upscaleCreative Upscaler
fal-ai/creative-upscalertext · file · image → imageimage_upscaleCreavax Image Auto
creavax-image-autotext · image → imagetext_to_image · image_to_imageCrystal Upscaler
clarityai/crystal-upscalerimage → imageimage_upscaleFLUX 2 Edit
fal-ai/flux-2/edittext · image → imageimage_to_imageFLUX.1 [dev]
fal-ai/flux/devtext → imagetext_to_imageFLUX.1 [schnell]
fal-ai/flux/schnelltext → imagetext_to_imageFLUX.1 Kontext [dev]
fal-ai/flux-kontext/devtext · image → imageimage_to_imageFLUX.1 Kontext [max]
fal-ai/flux-pro/kontext/maxtext · image → imageimage_to_imageFLUX.1 Kontext [pro]
fal-ai/flux-pro/kontexttext · image → imageimage_to_imageFLUX.2 [klein] 4B
fal-ai/flux-2/klein/4btext → imagetext_to_imageGoogle: Nano Banana (Gemini 2.5 Flash Image)
google/gemini-2.5-flash-imagetext · image → image · texttext_to_image · image_to_imageGoogle: Nano Banana 2 (Gemini 3.1 Flash Image)
google/gemini-3.1-flash-imagetext · image → image · texttext_to_image · image_to_imageGoogle: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
google/gemini-3.1-flash-lite-imagetext · image → image · texttext_to_image · image_to_imageGoogle: Nano Banana Pro (Gemini 3 Pro Image)
google/gemini-3-pro-imagetext · image → image · texttext_to_image · image_to_imageGPT Image 2 API
openai/gpt-image-2text → imagetext_to_imageGPT Image 2.5 Flare Edit
openai/gpt-image-2.5/flare/edittext · image → imageimage_to_imageIdeogram V4.0 Text to Image
ideogram/v4text → imagetext_to_imageIdeogram V4.0q Image to Image
ideogram/v4/image-to-imagetext · image → imageimage_to_imageKrea: Krea 2 Large
krea/krea-2-largetext · image → imagetext_to_image · image_to_imageKrea: Krea 2 Medium
krea/krea-2-mediumtext · image → imagetext_to_image · image_to_imageKrea: Krea 2 Medium Turbo
krea/krea-2-medium-turbotext · image → imagetext_to_image · image_to_imageMAI Image 2.5 Pro (Text to Image)
microsoft/mai-image-2.5-protext → imagetext_to_imageMeta: Muse Image
meta/muse-imagetext · image → imagetext_to_image · image_to_imageMicrosoft AI: MAI-Image-2.6
microsoft/mai-image-2.6text · image → imagetext_to_image · image_to_imageMicrosoft AI: MAI-Image-2.6 Flash
microsoft/mai-image-2.6-flashtext · image → imagetext_to_image · image_to_imageNano Banana 2
fal-ai/nano-banana-2/edittext · image · video · file · audio → imageimage_to_imageOpenAI: GPT Image 2.5 Flare
openai/gpt-image-2.5-flaretext · image → imagetext_to_image · image_to_imageOpenAI: GPT Image 2.5 Sunburst
openai/gpt-image-2.5-sunbursttext · image → imagetext_to_image · image_to_imageOpenAI: GPT-5.4 Image 2
openai/gpt-5.4-image-2text · image · file → image · texttext_to_image · image_to_image · document_to_imageQwen: Qwen Image 3
qwen/qwen-image-3text · image → imagetext_to_image · image_to_imageQwen: Qwen Image 3 Pro
qwen/qwen-image-3-protext · image → imagetext_to_image · image_to_imageRecraft Creative Upscale
fal-ai/recraft/upscale/creativeimage → imageimage_upscaleRecraft Crisp Upscale
fal-ai/recraft/upscale/crispimage → imageimage_upscaleRecraft V4.1 Text to Image Pro
fal-ai/recraft/v4.1/pro/text-to-imagetext · json → imagetext_to_imageRecraft: Recraft V4.1
recraft/recraft-v4.1text · image → imagetext_to_image · image_to_imageRecraft: Recraft V4.1 Pro
recraft/recraft-v4.1-protext · image → imagetext_to_image · image_to_imageSeedream 5.0 Pro Image Editing
bytedance/seedream/v5/pro/edittext · image → imageimage_to_imageSeedVR2
fal-ai/seedvr/upscale/imageimage → imageimage_upscaleSourceful: Riverflow V2.5 Fast
sourceful/riverflow-v2.5-fasttext · image → imagetext_to_image · image_to_imageSourceful: Riverflow V2.5 Pro
sourceful/riverflow-v2.5-protext · image → imagetext_to_image · image_to_imageTopaz Restore Image
topaz/restore/imageimage → imageimage_to_imageTopaz Upscale Image Generative
topaz/upscale/image/generativetext · image → imageimage_upscaleTopaz Upscale Image Precision
topaz/upscale/image/precisionimage → imageimage_upscaleUpscale Images
fal-ai/esrganimage → imageimage_upscalexAI: Grok Imagine Image 2.0
x-ai/grok-imagine-image-2.0text · image → imagetext_to_image · image_to_imageAmazon: Nova Lite 1.0
amazon/nova-lite-v1text · image → texttext_to_text · image_to_textAnthropic: Claude Fable 5.1
anthropic/claude-fable-5.1text · image · file → texttext_to_text · image_to_text · document_to_textAnthropic: Claude Opus 5.5
anthropic/claude-opus-5.5text · image · file → texttext_to_text · image_to_text · document_to_textCreavax Text Auto
creavax-text-autotext → texttext_to_textDeepgram: Nova-3
deepgram/nova-3text · audio → texttext_to_text · audio_to_textDeepSeek: DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731text → texttext_to_textDeepSeek: DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-exptext · image → texttext_to_text · image_to_textDeepSeek: DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flashtext · image → texttext_to_text · image_to_textGoogle: Gemini 3.1 Pro Preview
google/gemini-3.1-pro-previewtext · image · video · audio · file → texttext_to_text · image_to_text · video_to_text · audio_to_text · document_to_textGoogle: Gemini 3.7 Flash
google/gemini-3.7-flashtext · image · video · audio · file → texttext_to_text · image_to_text · video_to_text · audio_to_text · document_to_textGoogle: Gemini 3.8 Flash
google/gemini-3.8-flashtext · image · video · audio · file → texttext_to_text · image_to_text · video_to_text · audio_to_text · document_to_textMeta: Muse Spark 1.2 Contributor
meta/muse-spark-1.2-contributortext · image · video · audio · file → texttext_to_text · image_to_text · video_to_text · audio_to_text · document_to_textMicrosoft AI: MAI-Transcribe 2
microsoft/mai-transcribe-2text · audio → texttext_to_text · audio_to_textMoonshotAI: Kimi K2.6
moonshotai/kimi-k2.6text · image → texttext_to_text · image_to_textNVIDIA: Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55btext → texttext_to_textOpenAI: GPT Transcribe
openai/gpt-transcribetext · audio → texttext_to_text · audio_to_textOpenAI: GPT-5.4 Nano
openai/gpt-5.4-nanotext · image · file → texttext_to_text · image_to_text · document_to_textOpenAI: GPT-5.4 Pro
openai/gpt-5.4-protext · image · file → texttext_to_text · image_to_text · document_to_textOpenAI: GPT-5.4 Pro (batch)
openai/gpt-5.4-pro:batchtext · image · file → texttext_to_text · image_to_text · document_to_textOpenAI: GPT-5.6 Luna
openai/gpt-5.6-lunatext · image · file → texttext_to_text · image_to_text · document_to_textOpenAI: GPT-5.6 Sol
openai/gpt-5.6-soltext · image · file → texttext_to_text · image_to_text · document_to_textOpenAI: GPT-6 Astra
openai/gpt-6-astratext · image · file → texttext_to_text · image_to_text · document_to_textOpenAI: GPT-6 Astra Pro
openai/gpt-6-astra-protext · image · file → texttext_to_text · image_to_text · document_to_textOpenAI: Whisper Large V3
openai/whisper-large-v3text · audio → texttext_to_text · audio_to_textOpenAI: Whisper Large V3 Turbo
openai/whisper-large-v3-turbotext · audio → texttext_to_text · audio_to_textQwen: Qwen3 8B
qwen/qwen3-8btext → texttext_to_textQwen: Qwen3.8 27B
qwen/qwen3.8-27btext · image · video → texttext_to_text · image_to_text · video_to_textQwen: Qwen3.8 Max (0902)
qwen/qwen3.8-max-0902text · image · video → texttext_to_text · image_to_text · video_to_textSpaceXAI: Grok 4.20
x-ai/grok-4.20text · image · file → texttext_to_text · image_to_text · document_to_textSpaceXAI: Grok 4.3
x-ai/grok-4.3text · image · file → texttext_to_text · image_to_text · document_to_textTencent: Hy-MT2-1.8B
tencent/hy-mt2-1.8btext → texttext_to_textTencent: Hy4 preview
tencent/hy4-previewtext → texttext_to_textXiaomi: MiMo-V2.5
xiaomi/mimo-v2.5text · image · video · audio → texttext_to_text · image_to_text · video_to_text · audio_to_textXiaomi: MiMo-V2.5-Pro
xiaomi/mimo-v2.5-protext → texttext_to_textZ.ai: GLM 5.3 Flash
z-ai/glm-5.3-flashtext · image · video → texttext_to_text · image_to_text · video_to_textCreavax 3D Auto
creavax-3d-autotext · image → three_dtext_to_3d · image_to_3dHi3D Image to 3D
hitem3d/hi3d/v3.0/image-to-3dtext · image → three_dimage_to_3dHi3D Multiview to 3D
hitem3d/hi3d/v3.0/multi-view-to-3dtext · image → three_dtext_to_3d · image_to_3dHunyuan 3D Pro Image to 3D
fal-ai/hunyuan-3d/v3.1/pro/image-to-3dimage → three_dimage_to_3dHunyuan3d V3
fal-ai/hunyuan3d-v3/image-to-3dimage → three_dimage_to_3dHyper3D - Rodin V2.5 - Image to 3D
fal-ai/hyper3d/rodin/v2.5text · image · three_d · json → three_dimage_to_3dMeshy 6
fal-ai/meshy/v6/image-to-3dtext · image · file → three_dimage_to_3dMeshy 7.1 Image to 3D
meshy/v7.1/image-to-3dtext · image · file → three_dimage_to_3dMeshy 7.1 Multi Image to 3D
meshy/v7.1/multi-image-to-3dtext · image · file → three_dimage_to_3dSam 3
fal-ai/sam-3/3d-objectstext · file · image · three_d → three_dimage_to_3dTrellis
fal-ai/trellisimage · three_d → three_dimage_to_3dTrellis 2
fal-ai/trellis-2image → three_dimage_to_3dTripo H3.1 Image to 3D
tripo3d/h3.1/image-to-3dimage · three_d → three_dimage_to_3dTripo P2 Text to 3D
tripo3d/p2/text-to-3dtext → three_dtext_to_3dV7 Image to 3D
meshy/v7/image-to-3dtext · image · file → three_dimage_to_3dCreavax Upscale Auto
creavax-upscale-autoimage → imageimage_upscaleAlibaba: HappyHorse 1.0
alibaba/happyhorse-1.0text · image → videotext_to_video · image_to_videoAlibaba: HappyHorse 1.1
alibaba/happyhorse-1.1text · image → videotext_to_video · image_to_videoAlibaba: Wan 2.6
alibaba/wan-2.6text · image → videotext_to_video · image_to_videoAlibaba: Wan 2.7
alibaba/wan-2.7text · image → videotext_to_video · image_to_videoAlibaba: Wan 3.0
alibaba/wan-3.0text · image → videotext_to_video · image_to_videoAlibaba: Wan 3.0 Prime
alibaba/wan-3.0-primetext · image → videotext_to_video · image_to_videoBlack Forest Labs: FLUX Video Upscale
black-forest-labs/flux-video-upscaletext · video → videotext_to_video · video_reference_to_videoBlack Forest Labs: FLUX.3 Video
black-forest-labs/flux-3-videotext · image · video → videotext_to_video · image_to_video · video_reference_to_videoByteDance: Seedance 1.5 Pro
bytedance/seedance-1-5-protext · image → videotext_to_video · image_to_videoByteDance: Seedance 2.0
bytedance/seedance-2.0text · image · video · audio → videotext_to_video · image_to_video · video_reference_to_video · audio_to_videoByteDance: Seedance 2.0 Fast
bytedance/seedance-2.0-fasttext · image · video · audio → videotext_to_video · image_to_video · video_reference_to_video · audio_to_videoByteDance: Seedance 2.0 Mini
bytedance/seedance-2.0-minitext · image · video · audio → videotext_to_video · image_to_video · video_reference_to_video · audio_to_videoByteDance: Seedance 2.5
bytedance/seedance-2.5text · image · video · audio → videotext_to_video · image_to_video · video_reference_to_video · audio_to_videoCreavax Video Auto
creavax-video-autotext · image · video → videotext_to_video · image_to_video · video_reference_to_videoGoogle: Veo 3.1
google/veo-3.1text · image → videotext_to_video · image_to_videoGoogle: Veo 3.1 Fast
google/veo-3.1-fasttext · image → videotext_to_video · image_to_videoGoogle: Veo 3.1 Lite
google/veo-3.1-litetext · image → videotext_to_video · image_to_videoKling Video v3 Image to Video [Pro]
fal-ai/kling-video/v3/pro/image-to-videotext · image → videoimage_to_videoKling: Video O1
kwaivgi/kling-video-o1text · image → videotext_to_video · image_to_videoKling: Video v3.0 Pro
kwaivgi/kling-v3.0-protext · image → videotext_to_video · image_to_videoKling: Video v3.0 Standard
kwaivgi/kling-v3.0-stdtext · image → videotext_to_video · image_to_videoMiniMax: H3
minimax/hailuo-3text · image · video · audio → videotext_to_video · image_to_video · video_reference_to_video · audio_to_videoMiniMax: H3 Max
minimax/hailuo-3-maxtext · image → videotext_to_video · image_to_videoMiniMax: Hailuo 2.3
minimax/hailuo-2.3text · image → videotext_to_video · image_to_videoOpenAI: Sora 2 Pro
openai/sora-2-protext · image → videotext_to_video · image_to_videoRunway: Aleph 2.0
runway/aleph-2text · image · video → videotext_to_video · image_to_video · video_reference_to_videoRunway: Gen-4.5
runway/gen-4.5text · image → videotext_to_video · image_to_videoSeedance 2.5 Image to Video
bytedance/seedance-2.5/image-to-videotext · image → videoimage_to_videoSeedance 2.5 Reference to Video
bytedance/seedance-2.5/reference-to-videotext · image · video · audio → videovideo_reference_to_videoSpaceXAI: Grok Imagine Video
x-ai/grok-imagine-videotext · image → videotext_to_video · image_to_videoSpaceXAI: Grok Imagine Video 1.5
x-ai/grok-imagine-video-1.5text · image → videotext_to_video · image_to_videoWan
fal-ai/wan/v2.2-5b/text-to-video/fast-wantext · video → videotext_to_video