| --- |
| license: creativeml-openrail-m |
| tags: |
| - mlx |
| - apple-silicon |
| - diffusion |
| - stable-diffusion-xl |
| - sdxl |
| - anime |
| - text-to-image |
| base_model: OnomaAIResearch/Illustrious-XL-v2.0 |
| library_name: mlx-gen |
| pipeline_tag: text-to-image |
| --- |
| |
| # Illustrious-XL v2.0 — MLX pre-quantized tiers |
|
|
| Pre-quantized, packed-load tiers of [OnomaAIResearch/Illustrious-XL-v2.0](https://huggingface.co/OnomaAIResearch/Illustrious-XL-v2.0) |
| for on-device Apple-Silicon inference with [SceneWorks / `mlx-gen`](https://github.com/SceneWorks/mlx-gen) |
| (the `sdxl` generator). Each tier is a **self-contained diffusers turnkey snapshot** (U-Net + both |
| CLIP text encoders + VAE + tokenizers + scheduler + `model_index.json`) that loads directly. |
|
|
| Illustrious-XL v2.0 is the `v2.0-STABLE` snapshot — the last-annealing-phase checkpoint of a |
| cosine-annealing run, behaviourally distinct from (and more stable than) v1.0. It is architecturally |
| vanilla SDXL: dual CLIP-L + OpenCLIP-bigG, real CFG + negative prompt, eps prediction, VAE scaling |
| factor 0.13025, full sdxl-family LoRA support. Danbooru-tag prompting, ~30 steps at guidance 7.0. |
|
|
| ## Resolution note |
|
|
| Unlike v1.0, **v2.0 tends to duplicate the subject in wide frames** — a `1girl, solo` prompt can |
| render two characters once the frame gets wide (measured: it duplicates at 1344×768 and 1536×1536, |
| while tall and square frames stay clean). Prefer square or tall framing; the SceneWorks catalog |
| omits the widest aspect buckets for this model. |
|
|
| ## Provenance |
|
|
| Upstream ships a **single-file LDM checkpoint** (`Illustrious-XL-v2.0.safetensors`) that the MLX |
| `sdxl` loader cannot read. These tiers were produced offline with |
| [`scripts/build_sdxl_turnkey.py`](https://github.com/SceneWorks/SceneWorks/blob/main/scripts/build_sdxl_turnkey.py). |
| The conversion also normalizes two v2.0 quirks: a stray `position_ids` buffer (dropped) and a BF16 |
| VAE (kept dense at F32/F16 per tier). Component configs are the canonical SDXL descriptors. |
|
|
| ## Tiers |
|
|
| | dir | precision | what's quantized | |
| |----------|-----------|------------------| |
| | `q4/` (default) | group-wise affine Q4, group size 64 | U-Net Linears + both CLIP encoders | |
| | `q8/` | group-wise affine Q8, group size 64 | U-Net Linears + both CLIP encoders | |
| | `bf16/` | dense (f16 source mirror) | nothing | |
|
|
| The **VAE stays dense in every tier**. Convolutions, GroupNorms, and the CLIP token/position |
| embeddings also stay dense; only the true Linear projections are packed. Quantization is |
| byte-identical to `mlx-gen`'s load-time `nn.quantize` (bf16 cast, group 64). |
|
|
| ## License |
|
|
| CreativeML OpenRAIL-M, per the upstream model card. Commercial use OK, ungated; behavioral-use |
| restrictions apply. NOTE this differs from v1.0's SDXL (OpenRAIL++) license. |
|
|
