Source: https://docs.sogni.ai/sogni-create/studio/models/ # Models Sogni Studio supports the full open-weight diffusion lineage — Stable Diffusion 1.x and 2.x, SDXL, SD3 — plus newer transformer-style image, video, and audio models. The newest open-source image model in the lineup is [Krea 2 Turbo](https://www.sogni.ai/models/krea-2-turbo). Browse the full lineup in the Model Explorer or in the [Sogni Models catalog](https://www.sogni.ai/models), or import your own. ## [#](https://docs.sogni.ai/sogni-create/studio/models/#image-models)Image models - **[Krea 2 Turbo](https://www.sogni.ai/models/krea-2-turbo)** — Sogni's newest open-source image model (`krea2_turbo_fp8_scaled`). Fast few-step text-to-image and image-to-image, strong quoted text rendering, natural-language prompting, and output up to 2560px on the Supernet. - **Z-Image** — newer fast-inference family (`z_image_turbo_bf16`, `z_image_bf16`). Z-Image Turbo remains one of the most popular defaults for quick iteration. - **Chroma v.46/v.48** — popular stylized image workflows with distinctive color and texture. - **Flux family** — Flux.1 \[schnell\] provides fast prompt-driven image generation. - **SDXL & SDXL-Turbo / Lightning** — 1024×1024 native, fast distilled variants for 1–4 step generation. - **SD3** — triple text encoder (CLIP + OpenCLIP + T5), MMDiT denoiser, long prompt support up to 154 tokens. - **SD 1.5 / 2.x lineage** — hundreds of community-tuned variants; lightweight and fast. - **Sogni-tuned** — 🅂 Sogni.XL, Sogni Artist, Sogni Photo. ## [#](https://docs.sogni.ai/sogni-create/studio/models/#image-editing-models)Image editing models - **Qwen Image Edit 2511 Lightning** and **Qwen Image Edit 2511** — vision-language editing. Lightning is the fast edit path; both preserve identity and composition. Used under the hood by the Generative Filters in [Enhancing Images](https://docs.sogni.ai/sogni-create/studio/creating-images/enhancing-images/) and by chat-driven edits. ## [#](https://docs.sogni.ai/sogni-create/studio/models/#video-models)Video models - **[LTX-2.5](https://docs.sogni.ai/models/ltx-2-5/)** — production T2V, I2V/FLF, A2V, IA2V, and V2V through the official Distilled/Turbo workflows. V2V covers canny, depth, pose, detailer, inpaint, and outpaint; pose requires a source video plus a subject reference image. - **LTX-2.3** — retained rollback family and the source of voice ID-LoRA, transition-LoRA, and 10Eros workflows. - **Wan 2.2** — first-party Sogni video model. - **[ByteDance Seedance 2.0](https://www.sogni.ai/models/seedance-2-0)** — premium hosted video in full, Fast, and Mini tiers, including `seedance-2-0-mini` for lower-cost 720p iteration. - **[Alibaba HappyHorse 1.1](https://www.sogni.ai/models/happyhorse-1-1)** — premium hosted video for text-to-video, image-to-video, and 1-9 image-reference workflows with native synchronized audio. ## [#](https://docs.sogni.ai/sogni-create/studio/models/#audio-models)Audio models - **ACE-Step (turbo + SFT)** — music generation with lyrics, BPM, key, scale, time-signature, and a curated library of style presets. See [Creating Audio](https://docs.sogni.ai/sogni-create/studio/creating-audio/). ## [#](https://docs.sogni.ai/sogni-create/studio/models/#premium-spark-models)Premium Spark models Some hosted closed-weight models require **Premium Spark** (purchased via credit card, App Store IAP, or [USDC/USDT stablecoins](https://docs.sogni.ai/pricing/pay-with-crypto/)), not free Spark: - OpenAI GPT Image 2 - [ByteDance Seedance 2.0](https://www.sogni.ai/models/seedance-2-0), including Seedance 2.0 Mini and Fast - [Alibaba HappyHorse 1.1](https://www.sogni.ai/models/happyhorse-1-1) These appear in the Model Explorer when you're connected to Fast Supernet and have a Premium Spark balance. ## [#](https://docs.sogni.ai/sogni-create/studio/models/#where-models-run)Where models run Studio has two processing modes; not every model runs in both: - **On-device (CoreML)** — SD 1.x/2.x, SDXL, SDXL-Turbo, Z-Image. Free, private, one job at a time. See [Processing → On-Device](https://docs.sogni.ai/sogni-create/studio/advanced/processing/on-device/). - **Sogni Supernet** — every model above, including [Krea 2 Turbo](https://www.sogni.ai/models/krea-2-turbo), Z-Image Turbo, Chroma, Qwen Image Edit 2511 Lightning, LTX-2.5, LTX-2.3 rollback, [Seedance 2.0](https://www.sogni.ai/models/seedance-2-0), and [HappyHorse 1.1](https://www.sogni.ai/models/happyhorse-1-1). Costs Spark, runs in parallel batches. See [Processing → Supernet](https://docs.sogni.ai/sogni-create/studio/advanced/processing/supernet/). The Model Explorer's atom icon shows which models are available on the active Supernet (Fast vs Relaxed). On-device-only models are visible in the Explorer regardless of network state. ## [#](https://docs.sogni.ai/sogni-create/studio/models/#quantization)Quantization For on-device use, many models are available in **\[6-bit\]**, **\[4.5-bit\]**, and **\[4-bit\]** quantizations — three times lighter than the full versions, with minor quality differences. Useful on Macs with less than 16 GB unified memory. The full-precision versions are the default on machines with the headroom. ## [#](https://docs.sogni.ai/sogni-create/studio/models/#importing-your-own-models)Importing your own models Sogni can convert and run your own Stable Diffusion checkpoints. See [Importing Stable Diffusion Models](https://docs.sogni.ai/sogni-create/studio/models/importing-stable-diffusion-models/) for the SafeTensors / CKPT → Diffusers → CoreML pipeline. ## [#](https://docs.sogni.ai/sogni-create/studio/models/#see-also)See also [Available Models— current catalog link and Mac app availability notes.](https://docs.sogni.ai/sogni-create/studio/models/available-models/)[Model Types— explanation of each family.](https://docs.sogni.ai/sogni-create/studio/models/model-types/)[Model Storage & Deleting Models— where they live on disk.](https://docs.sogni.ai/sogni-create/studio/models/model-storage-and-deleting-models/)[About Switching Models on Supernet— switching without downloading.](https://docs.sogni.ai/sogni-create/studio/models/about-switching-models-on-supernet/)[Importing Stable Diffusion Models— bring your own.](https://docs.sogni.ai/sogni-create/studio/models/importing-stable-diffusion-models/) ▶️ **Tutorial video:** [Sogni AI Model Explorer: A World of Creative Styles](https://youtu.be/qLa6bbiThow?feature=shared)