Creavax
CREAVAX AI CONTEXT

Template rules +قدرات النماذج المختارة

سياق مرجعي قابل للقراءة آليًا لـ Template Builder في كريفاكس، يتضمن المخطط الحالي وقواعد الرسم البياني والقدرات الفعلية للنماذج المختارة والمرئية التي يستخدمها Template Builder.

Input → Agent Agent → Model Agent → Agent Agent → Output ممنوع Model → Output
01 / AI INSTRUCTIONS

How an AI should build a Creavax Template

السياق مستقل عن مزود الخدمة. تأتي مراجع النماذج فقط من مجموعة Admin Curated Models المرئية حاليًا؛ ومع ذلك يجب أن تبقى خانات النماذج المحمولة في القالب مبنية على القدرات والمتطلبات حتى يتمكن كريفاكس من اختيار نموذج نشط ومتوافق.

01

Create one valid .creavax-template.json object for Creavax Template Builder.

02

Use the live schema in this context as the package authority. Do not invent unsupported fields or input types.

03

Creavax Model Source-of-Truth Rule: use only models and capabilities explicitly declared by the Creavax Live Models Catalog exposed through this context and GET /ai-models/available. Do not analyze or infer model capabilities yourself.

04

Never infer, add or expand a capability from a model name, model family, provider name, provider marketing page, external documentation, general AI knowledge, similarity to another model, provider reputation or prior knowledge about that model.

05

If a capability, operation, input type, output type, feature or runtime control is absent or unknown in the Creavax live model contract, treat it as unsupported for Template compatibility. Unknown is not Supported.

06

Reference-image support is not equivalent to primary image input, image_to_image or image_edit. Treat those as supported only when Creavax explicitly declares them in the live model capability contract.

07

If your own knowledge about a model conflicts with Creavax, always follow Creavax. Do not choose, recommend or assume a real model that is not present in the current live_models catalog.

08

Before creating a Model slot, derive the Template requirements first, then inspect live_models only to understand what Creavax currently declares as available. Keep the slot provider-neutral and requirement-based; never hard-code the selected real model_key.

09

For numeric buyer controls, use the canonical Template input type reported by the schema. The current canonical numeric type is number; preserve numeric runtime values instead of routing them through select-option fallbacks.

10

Use live_models only to understand capabilities from the exact visible admin-curated model set exposed in Template Builder. The curated category membership controls discovery/availability; it does not redefine a model's real capability contract.

11

Keep template model slots portable and requirement-based. Do not hard-code provider IDs or model_key values inside template.models.

12

Connect user inputs to Agents, Agents to their Models, optional Agents to downstream Agents, and producing Agents to final Outputs.

13

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.

14

Every Agent MUST include a non-empty system_prompt. Missing, null, empty or whitespace-only system_prompt values are invalid. The prompt must describe the Agent role, responsibilities, input handling and how it should use its connected Models.

15

If a Model slot defines prompt_composition (final Prompt text), it must be non-empty. The literal {{prompt}} placeholder is optional: use it only when you want to choose where structured connected text inputs are inserted; without it, Creavax appends those structured inputs automatically.

16

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.

17

Model slots owned by the same Agent execute sequentially in target_port order: chatModel1 -> chatModel2 -> chatModel3. Parallel execution applies between independent Agents, not between Model slots inside one Agent.

18

Never connect a Model directly to an Output.

19

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.

20

Every requirements.inputs, requirements.outputs, requirements.operations and requirements.features entry is mandatory; Creavax intersects all constraints when resolving a real model.

21

Every model.setting_bindings[].setting is also a mandatory runtime capability/control before model selection. A model that lacks any bound control (for example aspect_ratio, duration_seconds, resolution, fps, quality or output_count) must not be selected or called.

22

Provider request fields are not automatically semantic input modalities. Prompt/instruction fields, JSON/config values, reference URLs, task IDs, masks, bounding boxes and provider-specific controls must not create a new generation operation unless the endpoint independently supports that operation.

23

For every setting_binding, the referenced input must exist, its type must be compatible with the setting, the setting must be a canonical supported runtime control, and the binding must not conflict with the Model slot requirements.

24

If a preferred or referenced model is unavailable or unregistered, Creavax may replace it only with an active model that satisfies the complete inputs + outputs + operations + features + required runtime-controls intersection.

25

Return valid JSON only when the user asks for the final Creavax template package.

02 / CURRENT SCHEMA

Use the live schema, not assumptions

Schema status: live. Supported input types: text · select · number · image · video · audio · three_d · file. SEO keywords: maximum 10.

Canonical package root
{
  "schema_version": "1.0",
  "type": "creavax_template",
  "template": "{...}"
}
03 / النماذج المختارة

90 نماذج Template Builder المختارة

تُحمّل النماذج من عضويات فئات Admin Curated Models المرئية نفسها التي يستخدمها Template Builder. تتحكم العضوية المختارة في الاكتشاف فقط؛ استخدم المدخلات والمخرجات ومجموعات القدرات والقدرات الفعلية لكل نموذج لتصميم المتطلبات، ولا تربط القالب المحمول بفئة أو مزود أو مفتاح نموذج محدد.

الفئة المختارةModel referenceI/Oالإمكانات
3DCreavax 3D Auto
creavax-3d-auto
text · image → three_dtext_to_3d · image_to_3d
3DHi3D Image to 3D
hitem3d/hi3d/v3.0/image-to-3d
image → three_dimage_to_3d
3DHi3D Multiview to 3D
hitem3d/hi3d/v3.0/multi-view-to-3d
image → three_dimage_to_3d
3DHunyuan 3D Pro Image to 3D
fal-ai/hunyuan-3d/v3.1/pro/image-to-3d
image → three_dimage_to_3d
3DHunyuan 3D Pro Text to 3D
fal-ai/hunyuan-3d/v3.1/pro/text-to-3d
text → three_dtext_to_3d
3DHyper3D - Rodin V2.5 - Image to 3D
fal-ai/hyper3d/rodin/v2.5
image → three_dimage_to_3d
3DHyper3D - Rodin V2.5 - Text to 3D
fal-ai/hyper3d/rodin/v2.5/text-to-3d
text · three_d · json → three_dtext_to_3d
3DMeshy 7.1 Image to 3D
meshy/v7.1/image-to-3d
image → three_dimage_to_3d
3DMeshy 7.1 Multi Image to 3D
meshy/v7.1/multi-image-to-3d
image → three_dimage_to_3d
3DMeshy 7.1 Text to 3D
meshy/v7.1/text-to-3d
text · file · image → three_dtext_to_3d
3DTrellis 2
fal-ai/trellis-2
image → three_dimage_to_3d
3DTripo P2 Image to 3D
tripo3d/p2/image-to-3d
image → three_dimage_to_3d
3DTripo P2 Text to 3D
tripo3d/p2/text-to-3d
text → three_dtext_to_3d
AudioCreavax Audio Auto
creavax-audio-auto
text → audiotext_to_audio
AudioDeepgram: Aura-2
deepgram/aura-2
text → audiotext_to_audio
AudioDeepgram: Nova-3
deepgram/nova-3
audio → textaudio_to_text
AudioElevenlabs Music v2.5
elevenlabs/music/v2.5
text · audio → audiotext_to_audio
AudioElevenlabs Sound Effects V2
fal-ai/elevenlabs/sound-effects/v2
text → audiotext_to_audio
AudioElevenlabs Tts Eleven V3
fal-ai/elevenlabs/tts/eleven-v3
text → audiotext_to_audio
AudioFish Audio: S2 Pro
fish-audio/s2-pro
text → audiotext_to_audio
AudioGoogle: Lyria 3 Pro Preview
google/lyria-3-pro-preview
text · image → audio · texttext_to_audio · image_to_audio
AudioMicrosoft AI: MAI-Transcribe 2
microsoft/mai-transcribe-2
audio → textaudio_to_text
AudioMicrosoft AI: MAI-Voice-2
microsoft/mai-voice-2
text → audiotext_to_audio
AudioMiniMax: Speech 2.8 HD
minimax/speech-2.8-hd
text → audiotext_to_audio
AudioMiniMax: Speech 2.8 Turbo
minimax/speech-2.8-turbo
text → audiotext_to_audio
AudioOpenAI: GPT Transcribe
openai/gpt-transcribe
audio → textaudio_to_text
AudioOpenAI: Whisper Large V3
openai/whisper-large-v3
audio → textaudio_to_text
AudioOpenAI: Whisper Large V3 Turbo
openai/whisper-large-v3-turbo
audio → textaudio_to_text
AudioQwen: Qwen-Audio-3.0-TTS Flash
qwen/qwen-audio-3.0-tts-flash
text → audiotext_to_audio
AudioQwen: Qwen-Audio-3.0-TTS Plus
qwen/qwen-audio-3.0-tts-plus
text → audiotext_to_audio
ImageBlack Forest Labs: FLUX.2 Flex
black-forest-labs/flux.2-flex
text · image → imagetext_to_image · image_to_image
ImageBlack Forest Labs: FLUX.2 Max
black-forest-labs/flux.2-max
text · image → imagetext_to_image · image_to_image
ImageByteDance Seed: Seedream 5.0 Pro
bytedance-seed/seedream-5-0-pro
text · image → imagetext_to_image · image_to_image
ImageChrono Edit
fal-ai/chrono-edit
text · image → imageimage_to_image
ImageCreavax Image Auto
creavax-image-auto
text · image → imagetext_to_image · image_to_image
ImageGoogle: Nano Banana 2 (Gemini 3.1 Flash Image)
google/gemini-3.1-flash-image
text · image → image · texttext_to_image · image_to_image
ImageGoogle: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
google/gemini-3.1-flash-lite-image
text · image → image · texttext_to_image · image_to_image
ImageGoogle: Nano Banana Pro (Gemini 3 Pro Image)
google/gemini-3-pro-image
text · image → image · texttext_to_image · image_to_image
ImageIdeogram V4.0 Text to Image
ideogram/v4
text → imagetext_to_image
ImageIdeogram V4.0q Image to Image
ideogram/v4/image-to-image
text · image → imageimage_to_image
ImageKrea: Krea 2 Large
krea/krea-2-large
text → imagetext_to_image
ImageMeta: Muse Image
meta/muse-image
text · image → imagetext_to_image · image_to_image
ImageMicrosoft AI: MAI-Image-2.6
microsoft/mai-image-2.6
text · image → imagetext_to_image · image_to_image
ImageMicrosoft AI: MAI-Image-2.6 Flash
microsoft/mai-image-2.6-flash
text · image → imagetext_to_image · image_to_image
ImageNano Banana 2
fal-ai/nano-banana-2/edit
text · image · video · audio · file → imageimage_to_image
ImageOpenAI: GPT Image 2.5 Flare
openai/gpt-image-2.5-flare
text · image → imagetext_to_image · image_to_image
ImageOpenAI: GPT Image 2.5 Sunburst
openai/gpt-image-2.5-sunburst
text · image → imagetext_to_image · image_to_image
ImageOpenAI: GPT-5.4 Image 2
openai/gpt-5.4-image-2
text · image · file → image · texttext_to_image · image_to_image · document_to_image
ImageQwen: Qwen Image 3 Pro
qwen/qwen-image-3-pro
text · image → imagetext_to_image · image_to_image
ImageRecraft: Recraft V4.1 Pro
recraft/recraft-v4.1-pro
text · image → imagetext_to_image · image_to_image
ImageSeedream 5.0 Pro Image Editing
bytedance/seedream/v5/pro/edit
text · image → imageimage_to_image
ImageSourceful: Riverflow V2.5 Pro
sourceful/riverflow-v2.5-pro
text · image → imagetext_to_image · image_to_image
TextAnthropic: Claude Fable 5.1
anthropic/claude-fable-5.1
text · image · file → texttext_to_text · image_to_text · document_to_text
TextAnthropic: Claude Opus 5.5
anthropic/claude-opus-5.5
text · image · file → texttext_to_text · image_to_text · document_to_text
TextCreavax Text Auto
creavax-text-auto
text → texttext_to_text
TextDeepSeek: DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash
text · image → texttext_to_text · image_to_text
TextGoogle: Gemini 3.8 Flash
google/gemini-3.8-flash
text · image · video · audio · file → texttext_to_text · image_to_text · video_to_text · audio_to_text · document_to_text
TextMoonshotAI: Kimi K2.6
moonshotai/kimi-k2.6
text · image → texttext_to_text · image_to_text
TextOpenAI: GPT-5.6 Luna
openai/gpt-5.6-luna
text · image · file → texttext_to_text · image_to_text · document_to_text
TextOpenAI: GPT-5.6 Sol
openai/gpt-5.6-sol
text · image · file → texttext_to_text · image_to_text · document_to_text
TextOpenAI: GPT-6 Astra
openai/gpt-6-astra
text · image · file → texttext_to_text · image_to_text · document_to_text
TextOpenAI: GPT-6 Astra Pro
openai/gpt-6-astra-pro
text · image · file → texttext_to_text · image_to_text · document_to_text
TextQwen: Qwen3.8 27B
qwen/qwen3.8-27b
text · image · video → texttext_to_text · image_to_text · video_to_text
TextQwen: Qwen3.8 Max (0902)
qwen/qwen3.8-max-0902
text · image · video → texttext_to_text · image_to_text · video_to_text
TextSpaceXAI: Grok 4.20
x-ai/grok-4.20
text · image · file → texttext_to_text · image_to_text · document_to_text
TextXiaomi: MiMo-V2.5-Pro
xiaomi/mimo-v2.5-pro
text → texttext_to_text
TextZ.ai: GLM 5.3 Flash
z-ai/glm-5.3-flash
text · image · video → texttext_to_text · image_to_text · video_to_text
UpscaleBria Increase Resolution: Upscale Images up to 4x Without Losing Detail | fal
bria/increase-resolution
image → imageimage_upscale
UpscaleClarity Upscaler
fal-ai/clarity-upscaler
image → imageimage_upscale
UpscaleCreavax Upscale Auto
creavax-upscale-auto
image → imageimage_upscale
UpscaleCrystal Upscaler
clarityai/crystal-upscaler
image → imageimage_upscale
UpscaleRecraft Creative Upscale
fal-ai/recraft/upscale/creative
image → imageimage_upscale
UpscaleRecraft Crisp Upscale
fal-ai/recraft/upscale/crisp
image → imageimage_upscale
UpscaleSeedVR2
fal-ai/seedvr/upscale/image/seamless
image → imageimage_upscale
UpscaleSeedVR2
fal-ai/seedvr/upscale/image
image → imageimage_upscale
UpscaleTopaz Restore Image
topaz/restore/image
image → imageimage_to_image
UpscaleTopaz Upscale Image Generative
topaz/upscale/image/generative
image → imageimage_upscale
UpscaleTopaz Upscale Image Precision
topaz/upscale/image/precision
image → imageimage_upscale
VideoAlibaba: Wan 3.0 Prime
alibaba/wan-3.0-prime
text · image → videotext_to_video · image_to_video
VideoBlack Forest Labs: FLUX.3 Video
black-forest-labs/flux-3-video
text · image · video → videotext_to_video · image_to_video · video_reference_to_video
VideoByteDance: Seedance 2.5
bytedance/seedance-2.5
text · image · video · audio → videotext_to_video · image_to_video · video_reference_to_video · audio_to_video
VideoCreavax Video Auto
creavax-video-auto
text · image · video → videotext_to_video · image_to_video · video_reference_to_video
VideoGoogle: Veo 3.1
google/veo-3.1
text · image → videotext_to_video · image_to_video
VideoGoogle: Veo 3.1 Fast
google/veo-3.1-fast
text · image → videotext_to_video · image_to_video
VideoKling: Video O1
kwaivgi/kling-video-o1
text · image → videotext_to_video · image_to_video
VideoKling: Video v3.0 Pro
kwaivgi/kling-v3.0-pro
text · image → videotext_to_video · image_to_video
VideoMiniMax: H3 Max
minimax/hailuo-3-max
text · image → videotext_to_video · image_to_video
VideoRunway: Aleph 2.0
runway/aleph-2
text · image · video → videovideo_reference_to_video
VideoRunway: Gen-4.5
runway/gen-4.5
text · image → videotext_to_video · image_to_video
VideoSpaceXAI: Grok Imagine Video 1.5
x-ai/grok-imagine-video-1.5
text · image → videotext_to_video · image_to_video
سياق الذكاء الاصطناعي في كريفاكس — قواعد القوالب وقدرات النماذج المختارة