Model directory21 image9 videoUpdated November 2026

Every AI image& video model.

21 image models and 9 video models, from a few dozen credits a render to HD video. Each runs in the same studio on the same credits, so switching models costs nothing but the render. There is no per-model subscription and credits never expire.

001
Grok Imagine 2.0 sample output

Grok Imagine 2.0New

GrokImage

Best-in-class instruction following, typography and editing with five references.

354 cr / imageSpecs
002
Z-Image Turbo sample output

Z-Image TurboHot

Open modelsImage

The most-liked new open model on Hugging Face. Photoreal in under a second.

54 cr / imageSpecs
003
Qwen Image Edit sample output

Qwen Image EditNew

Image editingImage

Attach up to three pictures and say what to change. Keeps faces, products and text intact.

216 cr / imageSpecs
004
Flux Dev sample output

Flux Dev

FluxImage

The full Flux model: strong prompt adherence at a low price.

130 cr / imageSpecs
005
Qwen Image 2512 sample output

Qwen Image 2512

QwenImage

The December 2025 open Qwen Image. Strong text, more natural people.

216 cr / imageSpecs
006
Flux Krea sample output

Flux Krea

FluxImage

Photographic output with less of the AI look.

216 cr / imageSpecs
007
Krea 2 Turbo sample output

Krea 2 Turbo

KreaImage

Krea's open-weight turbo model. The natural Krea look at draft speed.

162 cr / imageSpecs
008
Flux Kontext sample output

Flux Kontext

Image editingImage

Edit one picture by instruction. Very good at keeping everything you did not mention.

270 cr / imageSpecs
009
HunyuanImage 2.1 sample output

HunyuanImage 2.1

Open modelsImage

Tencent's open model built for native 2K output.

270 cr / imageSpecs
010

Grok Imagine

GrokImage

Sharp stills up to 2K with reference editing and multi-image composition.

142 cr / imageSpecs
011
Flux Schnell sample output

Flux SchnellBudget

FluxImage

The cheapest Flux by far. Built for iterating before you commit.

32 cr / imageSpecs
012
HiDream I1 sample output

HiDream I1

Open modelsImage

A 17B open foundation model with a painterly, highly detailed default.

259 cr / imageSpecs
013
Qwen Image sample output

Qwen Image

QwenImage

Excellent with text inside the image, in English and Chinese.

216 cr / imageSpecs
014
Flux 2 Klein Edit sample output

Flux 2 Klein Edit

Image editingImage

The fast Flux 2 editor. Up to three reference pictures, the lowest price of the editors.

173 cr / imageSpecs
015
Grok Imagine Quality sample output

Grok Imagine Quality

GrokImage

The slower, higher-fidelity Grok tier for final renders.

494 cr / imageSpecs
016
Z-Image sample output

Z-Image

Open modelsImage

The full Z-Image base model: more variety and control than Turbo.

108 cr / imageSpecs
017
Bria FIBO sample output

Bria FIBO

Open modelsImage

Trained only on licensed data. Built for commercial work that needs a clean provenance.

432 cr / imageSpecs
018
HiDream I1 Dev sample output

HiDream I1 Dev

Open modelsImage

The fast HiDream model. Dense, painterly detail at a draft price.

130 cr / imageSpecs
019
Lustly AI (Flux Lustly) sample output

Lustly AI (Flux Lustly)Open

Open modelsImage

Open Flux LoRA, routed through Hugging Face.

177 cr / imageSpecs
020
SLDR Flux sample output

SLDR FluxOpen

Open modelsImage

The highest-rated open Flux LoRA on the Hub.

177 cr / imageSpecs
021
Flux Open v2 sample output

Flux Open v2Open

Open modelsImage

Open Flux LoRA with strong contrast and detail.

177 cr / imageSpecs
001

Grok Imagine Video

GrokText to video

Text-to-video and image-to-video up to 720p.

494 cr / secSpecs
002

LTX-2New

LTXImage to video

Attach a still and it moves, with sound. The best value video model in the studio.

173 cr / secSpecs
003

Wan 2.2Open

Open modelsText to video

The open-weight Wan 2.2, routed through Hugging Face. The prompt decides everything.

648 cr / secSpecs
004

HunyuanVideo 1.5

Open modelsText to video

Tencent's open text-to-video model. Strong prompt following and natural motion.

432 cr / secSpecs
005
Wan 2.2 (image to video) sample output

Wan 2.2Open

Open modelsImage to video

Open image-to-video. Attach a still and it moves.

494 cr / secSpecs
006

Grok Imagine Video 1.5

GrokText to video

1080p image-to-video from xAI.

494 cr / secSpecs
007

Wan 2.2 5BBudget

Open modelsText to video

The small Wan 2.2. A five second clip for the price of a few images.

108 cr / secSpecs
008

Wan 2.1

Open modelsText to video

The earlier Wan release, with clips up to ten seconds.

648 cr / secSpecs
009

Wan 2.1

Open modelsImage to video

Animate a still for up to ten seconds.

648 cr / secSpecs
02

Head to head

The question is usually not which model is best but which of two is right for one job. These go through that choice on price, quality and what each is for.

Start generating

Image studioVideo studio