README: ZeroGPU setup and quota notes

README.md

@@ -30,15 +30,21 @@ Three modes in one model:
 - **Subject-driven generation** — place a subject from a photo into a new scene
 - **Canny-to-image** — generate from an edge map (auto-extraction available)
 
-## Running it (hardware requirements)
+## Running it
 
-This demo loads a video-generation backbone plus a 7B text encoder and several
-vision encoders. Recommended: **A100 (40 GB+)**. For smaller GPUs, set the
-environment variable `FF_OFFLOAD=true` (much slower, CPU offloading).
+Built for **ZeroGPU** (`xlarge` slices, 96 GB): generation functions are
+decorated with `@spaces.GPU`, and torch is pinned to **2.8.0** (the closest
+ZeroGPU-supported version to the authors' 2.6.0 pin). It also runs unchanged
+on a persistent GPU (A100 40 GB+ recommended; `FF_OFFLOAD=true` for smaller
+GPUs at a large speed cost) — the decorator is a no-op off ZeroGPU.
 
 **First run downloads ~60 GB of checkpoints.** On Spaces, attach persistent
 storage and set `FF_CKPT_DIR=/data/ckpts` so this happens once.
 
+**Quota note:** a 50-step generation takes a few minutes of GPU time and
+`xlarge` consumes 2× daily quota — free accounts (5 min/day) get roughly one
+image per day, PRO accounts (40 min/day) get several.
+
 Required secret: `HF_TOKEN` — the pipeline pulls the **gated**
 [FLUX.1-Redux-dev](https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev)
 vision encoder, so the token's account must have accepted its license.