Rewrite model card: production settings, samples, usage

README.md

@@ -1,3 +1,125 @@
 ---
 license: unknown
+pipeline_tag: text-to-image
+tags:
+  - text-to-image
+  - stable-diffusion-xl
+  - sdxl
+  - checkpoint
+base_model:
+  - stabilityai/stable-diffusion-xl-base-1.0
 ---
+
+# SDXL Checkpoints — Juggernaut XL v9 + Illustrious Anime v4
+
+Full single-file SDXL checkpoints served by the giga-images sidecar, which registers one switchable model per checkpoint found on disk.
+
+> **What this repo is:** a repacked/quantized build of the model, laid out exactly as the giga-images sidecar expects it. The settings below are not suggestions — they are the presets that sidecar runs in production, read directly from its model catalog.
+
+---
+
+## Samples
+
+_No sample renders published for this repo yet._
+
+---
+
+## Production settings
+
+These are the live `default_params` for catalog key **`sdxl-juggernaut-xl-v9`** (engine `sdxl`, residency slot `image`).
+
+| Parameter | Production value | Meaning |
+|---|---|---|
+| `width` | `1024` | Output width in pixels |
+| `height` | `1024` | Output height in pixels |
+| `steps` | `35` | Denoising steps |
+| `guidance` | `7.5` | Guidance scale |
+| `preview_every` | `5` | Emit a TAESD preview every N steps |
+| `strength` | `0.75` | img2img denoise strength (1.0 = ignore the input image) |
+
+**Job types served:** `txt2img`, `img2img`
+
+### Notes and gotchas
+
+- **This repo holds two checkpoints and the shared SDXL tokenizers** — there is no unet/VAE folder, because each `.safetensors` here is a complete single-file checkpoint.
+- **Checkpoints are discovered dynamically.** The sidecar scans `models/sdxl/` and `models/sdxl/combined/` at startup and registers one `image`-slot model per checkpoint over 1 GiB, keyed `sdxl-<slugified-filename>`. Drop a new checkpoint in and restart to pick it up.
+- Both checkpoints run at **float32** in this engine, so expect a larger memory footprint than a fp16 SDXL deployment.
+- Unlike every other model here, SDXL uses a **real CFG schedule** — guidance 7.5, 30 steps. It is not a distilled/turbo build.
+
+---
+
+## Usage
+
+The sidecar exposes a small HTTP + WebSocket API. Submit a job with the production preset:
+
+```bash
+curl -X POST http://127.0.0.1:7860/jobs \
+  -H 'Content-Type: application/json' \
+  -d '{
+  "type": "txt2img",
+  "model_key": "sdxl-juggernaut-xl-v9",
+  "params": {
+    "prompt": "a red apple on a wooden table, studio photograph",
+    "width": 1024,
+    "height": 1024,
+    "steps": 35,
+    "guidance": 7.5,
+    "preview_every": 5,
+    "strength": 0.75
+  }
+}'
+```
+
+Poll the job, then read the durable artifact path:
+
+```bash
+curl http://127.0.0.1:7860/jobs/<job_id>
+# -> {"status": "complete", "output_url": "/outputs/<model_key>/<job_id>.png", ...}
+```
+
+Connect to `ws://127.0.0.1:7860/ws` for `progress`, `preview` (TAESD WebP), and `complete` events.
+
+> `output_url` is durable and survives restarts — persist that one. `/jobs/{id}/result` is served from an in-memory table that is dropped on restart.
+
+### Catalog entry
+
+The sidecar registers this model as:
+
+```python
+ModelSpec(
+    key='sdxl-juggernaut-xl-v9',
+    slot='image',
+    label='SDXL (juggernaut_XL_v9)',
+    engine='sdxl',
+    job_types=('txt2img', 'img2img'),
+    default_params={'width': 1024, 'height': 1024, 'steps': 35, 'guidance': 7.5, 'preview_every': 5, 'strength': 0.75},
+)
+```
+
+---
+
+## Files
+
+| File | Size | Role |
+|---|---|---|
+| `combined/juggernaut_XL_v9.safetensors` | 6.62 GB | transformer (main weights) |
+| `combined/illustrious_Anime_v4.safetensors` | 6.53 GB | full single-file SDXL checkpoint |
+| `config/tokenizer/tokenizer.json` | 3.47 MB | tokenizer / processor |
+| `config/tokenizer_2/tokenizer.json` | 3.47 MB | tokenizer / processor |
+| `config/tokenizer/vocab.json` | 1.01 MB | tokenizer / processor |
+| `config/tokenizer_2/vocab.json` | 1.01 MB | tokenizer / processor |
+| `config/tokenizer/merges.txt` | 512.32 KB | tokenizer / processor |
+| `config/tokenizer_2/merges.txt` | 512.32 KB | tokenizer / processor |
+| `config/tokenizer/tokenizer_config.json` | 737 B | tokenizer / processor |
+| `config/tokenizer_2/tokenizer_config.json` | 725 B | tokenizer / processor |
+| `config/model_index.json` | 609 B | config |
+| `config/tokenizer/special_tokens_map.json` | 472 B | tokenizer / processor |
+| `config/tokenizer_2/special_tokens_map.json` | 460 B | tokenizer / processor |
+
+---
+
+## Provenance
+
+- **Upstream base model:** [`stabilityai/stable-diffusion-xl-base-1.0`](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) (upstream license: openrail++)
+- **This build:** requantized / relaid-out for the giga-images sidecar. Weights are not retrained; only the format and directory layout differ.
+- **License:** left as `unknown` in this repo's metadata. Refer to the upstream model's license for redistribution and commercial-use terms — several of these bases are non-commercial.