Multimodal model · Coming Soon

FLUX 3 Coming Soon to ClipCanva

FLUX 3 is Black Forest Labs’ upcoming multimodal model for image, video, audio, language, and action prediction. ClipCanva is preparing FLUX 3 support while public access, model IDs, pricing, and limits are confirmed.

Browse Available ModelsCreate FLUX-Style Images

What Is FLUX 3?

One model designed to understand and create images, video, audio, language, and motion.

Image generation and editing

Create and revise images across styles, compositions, aspect ratios, and resolutions.

Video with native audio

Create video from text, images, clips, keyframes, and audio-aware inputs.

Language and action prediction

Connect prompts, sound, motion, and physical change in one multimodal system.

Specification

FLUX 3 Availability

What is confirmed today and what is still pending.

Current statusAnnounced with phased early access
Public accessAvailability and model IDs pending
ClipCanva supportIn preparation
KIE APIUpcoming page published; endpoints, pricing, and limits pending

What FLUX 3 Is Expected to Support

Final controls and limits may change as early access expands.

ImagesGeneration and editing with complex prompts, multilingual text, style, and composition control.
Video and audioText-to-video, image-to-video, video-to-video, keyframes, native audio, and dialogue.
Creative controlReference images, clips, multi-shot workflows, animated text, and controlled scene changes.
Compare

Create Now While FLUX 3 Is Coming

Use these ClipCanva workflows today.

FLUX 3Coming soon for multimodal image, video, audio, and action workflows.
FLUX-Style Image GeneratorDetailed images, product visuals, illustrations, and social graphics.Open
FLUX Video AITurn FLUX-style still images into short videos.Open
Text to ImageCreate products, campaigns, thumbnails, posters, and visual concepts.Open
Image to VideoAnimate uploaded images with subject and camera motion.Open
Text to VideoGenerate short videos from scene descriptions.Open
Video EffectsApply visual effects and focused motion workflows.Open
AI ModelsBrowse current image and video models.Open

FLUX 3 FAQ

What is FLUX 3?
FLUX 3 is Black Forest Labs’ upcoming multimodal model for image, video, audio, language, and action prediction.
When will FLUX 3 be available on ClipCanva?
FLUX 3 is in phased early access. ClipCanva is preparing support while public availability, model IDs, pricing, and limits are confirmed.
What can FLUX 3 create?
Expected capabilities include image generation and editing, video generation, native audio, dialogue, references, keyframes, and multi-shot workflows. Final public features may change.
Is there a FLUX 3 API?
KIE has published an upcoming FLUX 3 API page. Endpoints, official model IDs, pricing, limits, and production documentation are still pending.
What can I use before FLUX 3 is ready?
Use ClipCanva’s FLUX-style image generator, FLUX Video AI, Text to Image, Image to Video, Text to Video, Video Effects, and current AI models.