Models and the Model Hub

Models and the Model Hub

Smart model detection and architecture presets

MooshieUI recognizes a broad set of model architectures and auto-applies an optimal sampler, scheduler, steps, CFG, and resolution for each. Families include (among others): SD 1.5, SD 2.x, SDXL, Illustrious/NoobAI, Pony Diffusion, SD3/SD3.5, the Flux family (Flux.1 Dev/Schnell/Krea and Flux 2 Klein variants), Chroma, Z-Image, Wan, Qwen, AuraFlow, PixArt, HunyuanDiT, Stable Cascade, Kolors, Anima (COSMOS), Mugen (SDXL + Flux2 VAE), and Nanosaur (1.2B DiT).

Behavior worth knowing:

• Accelerated models (turbo, lightning, lcm, hyper in the name) get reduced steps and lower CFG automatically.
• Rectified flow models inject the correct ModelSampling node with architecture-specific shift values.
• FluxGuidance is injected for Flux Dev; Flux Schnell is detected and skipped.
• Hash-based identification - models are recognized by SHA256 hash (CivitAI AutoV2), so renamed files still resolve.
• Structural identification - when filename, sidecar, and hash signals are inconclusive, MooshieUI inspects the safetensors tensor keys. This recognizes Wan2.1/Anima (COSMOS) DiT checkpoints by their transformer block structure, so an Anima fine-tune renamed without an anima/yume token (for example PerfectDeliberate) is still classified as the Anima family. This matters for ControlNet, which must route through the Anima LLLite path for these models. See ControlNet and Style Transfer.

Recommended models (auto-download)

A few curated checkpoints can auto-download on selection with a live progress bar and file size, including a NoobAI/Illustrious checkpoint and Anima Base v1.0 (~13 GB). The exact recommended list evolves between releases, so treat the in-app list as the source of truth.

Model Hub (CivitAI / HuggingFace browser)

Browse and download models from inside the app:

• Filter by type (Checkpoint, LoRA, ControlNet, Upscaler, VAE, Textual Inversion), sort (Highest Rated, Most Downloaded, Newest), time period, architecture, and file format (SafeTensor, PickleTensor, GGUF, Diffusers, CoreML, ONNX, Other).
• Add a CivitAI API key for gated content.
• One-click download routes the file to the correct folder with a real-time progress bar.

CivitAI-enriched galleries

The bottom-panel LoRA and Checkpoint galleries auto-fetch CivitAI metadata (name, preview images, model ID) for your local files and cache it for 24 hours. The LoRA gallery lets you set a thumbnail from a CivitAI image URL. Both support search and sort by name/date/family, plus right-click actions.

Model manager

In Settings you can manage local model files across categories (checkpoints, loras, vae, upscale, controlnet, embeddings, ultralytics, text encoders, diffusion models): search by filename, delete files, move files between configured directories, and see total disk usage per category.

Model requests (multi-user)

In hosted/multi-user deployments, non-admin users can request a model download by CivitAI URL. Admins and moderators see a pending/approved/denied queue and can approve (which starts the download) or deny with a reason. See Server, LAN and Multi-User.