AI models on Floniks
Pick the model per shot, not per subscription. Every model below draws from the same credit balance, with no minimum spend.
Google · Image editing
Nano Banana
Creative edits from a plain-language prompt, with up to 10 reference images.
Kuaishou · Image to video
Kling
V3 Pro, 2.6, 3.0 Turbo and O3 Pro, billed per render from one balance.
Google · Image generation and editing
Nano Banana Pro
The highest-fidelity option when the result has to ship, not just look promising.
Google · Image to video
VEO 3.1 Quality
Fixed 8 seconds, up to 4K. The highest production value on the platform.
ByteDance · Multimodal to video
Seedance 2.0
The multimodal tier: combine up to 9 images, 3 videos and 3 audio clips in one render.
Pixverse · Image to video
Pixverse V6
Wide resolution and duration range, built for volume rather than peak quality.
Google · Text to image
Nano Banana 2
Wide stylistic range from a text prompt, 0.5K to 4K, built for volume.
MiniMax · Image to video
Hailuo
2.0, 2.3 and 2.3 Pro plus text-to-video, all billed per render.
OpenAI · Image generation and editing
GPT-Image-2
The model to reach for when the brief is exact and the text has to be readable.
ByteDance · Image editing
Seedream 4
Style transfer, object replacement and background swaps in around 18 seconds.
Alibaba · Image editing
Qwen Image Edit
The model that actually gets Chinese characters right inside an image.
MiniMax · Image, text and reference to video
MiniMax H3
Image, text or reference-driven video at 2K, 4 to 15 seconds, 21:9 through 9:16.
Kuaishou · Image to video
Kling 2.6
720p standard or 1080p pro, 5 or 10 seconds, consistent results.
Alibaba · Motion transfer
Wan 2.2 Animate
Take the movement from one video and put it on a still character.
ByteDance · Image generation and editing
Seedream 5 Pro
Built for consistency work: the same character or product across an entire set.
Lightricks · Image to video and lip sync
LTX 2.3
The highest resolution option, plus a talking-head mode driven by audio.
Alibaba · Image, text and reference to video
Wan 2.7
Up to 5 reference images to keep the same person across every shot.
ByteDance · Audio to video
OmniHuman v1.5
A portrait plus an audio track becomes a person who moves like one.