Dynamic GPU capability detection: probe CC, VRAM, feature flags, pick best model

Replaces fixed tier table with real hardware probing and dynamic model selection.

gpu_detect.py — complete rewrite:
- Reads torch.cuda.get_device_properties + mem_get_info for actual free VRAM
- Detects: fp16 (CC≥6.0), bf16 (CC≥8.0), fp8 (CC≥8.9 Ada/Hopper),
           int8 (CC≥7.0), tensor_cores (CC≥7.0), xformers presence
- Pre-Pascal (CC<6.0): effective_vram halved (fp32 weights are 2× larger)
- Subtracts 400MB driver overhead from free VRAM before model selection
- _select_txt2img / _select_inpaint / _select_img2img / _select_upscale:
    eff≥20GB  → FLUX.1-schnell (no offload)
    eff≥10GB  → FLUX.1-schnell (model_cpu_offload)
    eff≥7.5GB → SDXL
    eff≥5.5GB → SDXL + attention_slicing
    eff≥3.5GB → SD 2.1
    eff≥2.5GB → SD 2.1-base + attention_slicing
    eff≥1.7GB → SD 1.5
    else      → SD 1.5 + sequential_cpu_offload
- ModelSpec carries: model_id, family, memory_opt, native_res, vram_fp16_gb
- Warnings: old CC, pre-Pascal fp32, fp8 upgrade hint, xformers install tip
- Compatibility shim get_model_ids() retained for existing callers
- infer_spec_from_model_id() auto-detects family from HF_MODEL_* overrides

local_diffusion.py — refactored to use ModelSpec:
- Reads spec from GpuCapabilities.recommended[op] instead of tier table
- FLUX.1-schnell: FluxPipeline / FluxImg2ImgPipeline, 4 steps, guidance=0.0
- SD families: family-aware pipeline class selection (sd15/sd2x/sdxl)
- Memory opts applied per ModelSpec.memory_opt field
- xformers attention enabled automatically when xformers detected

gpu_status.py — richer response:
- Exposes all feature flags (fp16/bf16/fp8/int8/tensor_cores/xformers)
- Returns full ModelSpec per operation (model_id, family, memory_opt, native_res)

ai_tools.py — /api/config exposes:
- gpu_vram_total, gpu_vram_free, gpu_cc, gpu_fp16, gpu_bf16, gpu_fp8,
  gpu_tensor_cores, gpu_eff_vram, local_gpu_warnings

requirements.gpu.txt:
- diffusers bumped to >=0.29.0 (FLUX pipeline added in 0.29)
- transformers bumped to >=4.40.0
- sentencepiece added (FLUX T5 tokenizer)

scripts/gpu_setup.py:
- Prints full model table at startup (op → model_id, family, memory_opt, res)
- Shows all feature flags in one line

https://claude.ai/code/session_01WVDg7amsy1TTtxvpku7bcM

backend/app/routers/ai_tools.py

@@ -335,13 +335,21 @@ async def get_config():
             "lama": lama_available(),
             "rembg": rembg_available(),
             "opencv": True,
-            "gpu_detected": gpu_available(),
-            "gpu_backend": gpu_info.backend,
-            "gpu_device": gpu_info.device_name,
-            "gpu_vram_gb": gpu_info.vram_gb,
-            "gpu_tier": gpu_info.tier,
+            "gpu_detected":    gpu_available(),
+            "gpu_backend":     gpu_info.backend,
+            "gpu_device":      gpu_info.device_name,
+            "gpu_vram_total":  gpu_info.vram_total_gb,
+            "gpu_vram_free":   gpu_info.vram_free_gb,
+            "gpu_cc":          gpu_info.compute_capability,
+            "gpu_fp16":        gpu_info.fp16,
+            "gpu_bf16":        gpu_info.bf16,
+            "gpu_fp8":         gpu_info.fp8,
+            "gpu_tensor_cores": gpu_info.tensor_cores,
+            "gpu_tier":        gpu_info.tier,
+            "gpu_eff_vram":    gpu_info.effective_vram_gb,
             "local_gpu_available": gpu_info.backend in ("cuda", "mps"),
             "local_gpu_capabilities": gpu_info.capabilities,
+            "local_gpu_warnings": gpu_info.warnings,
         },
         "remote": {
             "default_provider": default_name,