Handle old/low-VRAM GPUs and document nvidia-container-toolkit requirement

GPU tier table extended:
  ultra   ≥16 GB → SDXL (unchanged)
  high    8-16 GB → SDXL (unchanged)
  medium  4-8 GB → SD 2.x (unchanged)
  legacy  2-4 GB → SD 1.5 (~1.7 GB fp16)  ← new: GTX 970/1060/RX 580 etc.
  minimal <2 GB  → SD 1.5 + sequential CPU offload  ← new: very old/integrated GPUs

gpu_detect.py:
- Detects CUDA compute capability (CC); fp16 disabled for CC < 6.0 (pre-Pascal)
- GpuInfo gains compute_capability and warnings fields
- _make_warnings() emits human-readable warnings for low VRAM and old CC
- model tier fallback updated from 'low' to 'legacy'

local_diffusion.py:
- minimal/legacy tiers use enable_sequential_cpu_offload() + enable_attention_slicing(1)
- target resolution per tier: ultra/high=1024, medium=768, legacy/minimal=512
- .to(device) skipped when sequential CPU offload is active

gpu_status.py:
- Response now includes compute_capability and warnings

docker-compose.gpu.yml:
- Full nvidia-container-toolkit install instructions in header comment
- nvidia-docker2 (legacy) fallback documented as comment block inline
- AMD ROCm swap-in instructions added
- GPU tier table documented in header

scripts/gpu_setup.py:
- Prints compute capability, fp16 status, tier, and model selection at startup
- Prints per-tier warnings (old CC, low VRAM)

https://claude.ai/code/session_01WVDg7amsy1TTtxvpku7bcM

backend/app/main.py

@@ -39,10 +39,13 @@ async def lifespan(app: FastAPI):
     ):
         from app.services.gpu_detect import get_cached_gpu_info
         info = get_cached_gpu_info()
+        cc_str = f" | CC={info.compute_capability}" if info.compute_capability else ""
         print(
-            f"[gpu] {info.device_name} | {info.vram_gb:.1f} GB | tier={info.tier} | "
-            f"backend={info.backend}"
+            f"[gpu] {info.device_name} | {info.vram_gb:.1f} GB{cc_str} | "
+            f"tier={info.tier} | fp16={info.fp16}"
         )
+        for w in info.warnings:
+            print(f"[gpu] ⚠ {w}")
         if settings.auto_download_models:
             # Download model weight files to disk cache in background so first
             # user request loads from local disk instead of the internet.