| --- |
| title: DiffusionDB SD 1.5 LoRA — Inference |
| emoji: ⚙️ |
| colorFrom: gray |
| colorTo: indigo |
| sdk: docker |
| app_port: 7860 |
| pinned: false |
| license: creativeml-openrail-m |
| models: |
| - whosouravsharma/diffusiondb-sd15-lora |
| --- |
| |
| # Inference backend |
|
|
| Generation backend for |
| [`diffusiondb-sd15-lora`](https://huggingface.co/spaces/whosouravsharma/diffusiondb-sd15-lora). |
| Loads Stable Diffusion 1.5 plus the LoRA adapter and exposes a single |
| `/generate` endpoint. The minimal interface is for debugging; the real client |
| is the UI Space. |
|
|
| **This is the Space that needs a GPU.** `t4-small` renders a 512×512 image in |
| a few seconds; CPU takes minutes. |
|
|
| ```python |
| from gradio_client import Client |
| |
| client = Client("whosouravsharma/diffusiondb-sd15-lora-inference") |
| image, seed = client.predict( |
| "a steampunk owl inside a glass jar, intricate detail", # prompt |
| "", # negative_prompt |
| 25, # steps |
| 7.5, # guidance |
| 1.0, # lora_scale — 0 renders vanilla SD 1.5 |
| -1, # seed, -1 for random |
| api_name="/generate", |
| ) |
| ``` |
|
|
| ## Files |
|
|
| - `app.py` — Gradio app exposing `/generate` |
| - `src/pipeline.py` — model loading and generation, no Gradio dependency |
| - `src/infer.py` — CLI: `python3 -m src.infer "a prompt"` |
| - `src/tracing.py` — optional LangSmith tracing + structured logging |
| - `scripts/compare_checkpoints.py` — contact sheet across checkpoints/scales |
|
|
| ## Observability |
|
|
| Every generation logs one structured line — seed, steps, guidance, |
| lora_scale, device, latency, ms/step — with no configuration needed. |
| |
| LangSmith tracing is opt-in. Unset, `src/tracing.py` no-ops and the package |
| is never imported, so the serving path is unchanged: |
| |
| ```bash |
| export LANGSMITH_TRACING=true |
| export LANGSMITH_API_KEY=<key> |
| export LANGSMITH_PROJECT=diffusiondb-sd15-lora-inference |
| ``` |
| |
| On the Space, set `LANGSMITH_API_KEY` as a **secret** and the other two as |
| plain **variables**. |
| |
| Traces carry the generation parameters, the resolved device/dtype/checkpoint, |
| and latency — but never the image itself: LangSmith stores run I/O as JSON, |
| and a base64 512×512 PNG is ~400 KB per run, which gets truncated and makes |
| the trace view unusable. Set `LANGSMITH_LOG_IMAGES=1` to attach a ~10 KB WEBP |
| thumbnail instead (`LANGSMITH_THUMBNAIL_PX` controls the size). |
| |
| A generation that arrives from the UI Space is not a trace of its own. The |
| UI sends `langsmith-trace` and `baggage` headers with its `gradio_client` |
| call; `app.py` reads them off the Gradio request and continues that trace, |
| so the `sd15_lora_generate` run here lands as a child of the UI's |
| `ui_generate` run instead of in a separate tree. The visitor location the |
| UI puts in baggage rides along, so it appears on this run too — the |
| backend never sees the visitor directly, since the call reaches it |
| server-to-server from the UI Space. A direct API call sends no such |
| headers and simply starts its own trace. |
|
|
| ## Comparing checkpoints |
|
|
| Fixed seed, fixed prompts, every (checkpoint, lora_scale) combination tiled |
| into one labelled PNG — the direct way to see what the adapter changed: |
| |
| ```bash |
| python3 -m scripts.compare_checkpoints \ |
| --checkpoints base checkpoint-4240 \ |
| --scales 0.0 0.5 1.0 --seed 42 --out sweep.png |
| ``` |
| |
| With tracing on, the sweep is one parent run with a child run per image. |
|
|
| ## Environment |
|
|
| | Variable | Default | Effect | |
| | --- | --- | --- | |
| | `BASE_MODEL` | `stable-diffusion-v1-5/stable-diffusion-v1-5` | base checkpoint | |
| | `LORA_REPO` | `whosouravsharma/diffusiondb-sd15-lora` | adapter repo | |
| | `LORA_CHECKPOINT` | `checkpoint-4240` | `base` skips the adapter | |
| | `ATTENTION_SLICING` | `auto` | `auto` = MPS only; `true`/`off` to force | |
| | `LOG_LEVEL` | `INFO` | log verbosity | |
|
|
| Weights are pulled from the model repo on first request, not baked into the |
| image, so switching checkpoints is a `LORA_CHECKPOINT` env change. The fp16 |
| variant is used on GPU, so the cold-start download is ~2 GB rather than ~4. |
|
|
| **Batch seeds:** image *i* of a batch is generated with `seed + i`, so any |
| single image is reproducible on its own at that seed with `--count 1`. |
|
|
