Open Source · Transparent

Model Registry

Every AI model powering WokGen is listed here — with its license, provider, and source. No black boxes. No proprietary lock-in.

Image Generation

FLUX.1-schnell

vv1
Apache-2.0

State-of-the-art image generation in 4 steps. Exceptional quality-to-speed ratio.

Stable Diffusion XL 1.0

vSDXL 1.0
CreativeML

Flagship SDXL model from Stability AI. High-resolution 1024×1024 native output.

Deliberate v3

vv3
CreativeML

Community favourite for photorealistic and detailed imagery. Versatile style range.

DreamShaper 8

vv8
CreativeML

Highly versatile — adapts to digital art, illustration, and photo styles effortlessly.

Language Model

Llama 3.3 70B

v3.3-70B-Instruct
Llama 3.3 Community

State-of-the-art open large language model from Meta. Powers Eral AI companion.

Mistral 7B

v0.3
Apache-2.0

Efficient 7B parameter language model. Fast inference with strong reasoning.

Text-to-Speech

Kokoro-82M

v82M
Apache-2.0

High-quality text-to-speech at only 82M parameters. Multiple voice styles supported.

Bark

vsuno/bark
MIT

Expressive multi-speaker TTS with emotion, music, and sound effects. Highly creative.

Microsoft Edge TTS

vedge-tts
Proprietary / Free

400+ voices in 100+ languages. Enterprise-quality neural TTS, free to use.

Provider Health

Status is manually updated. All providers shown as operational unless otherwise noted.

Together AIPrimary LLM + image API
operational
Hugging FaceModel hosting + inference
operational
Stable HordeDistributed GPU inference
operational
GroqUltra-fast LLM inference
operational
PollinationsUnlimited free image gen
operational
ElevenLabsSFX generation
operational
edge-ttsMicrosoft neural TTS
operational

Want to add a model?

WokGen is open-source. Open a PR on GitHub to add models, providers, or integrations.