Skip to content

feat: image-generation-with-stablediffusion #330

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
+165 −1,222
Open

feat: image-generation-with-stablediffusion #330

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8138de3
[test] Notebook output and new requirements
gabisponciano Nov 11, 2025
3c0746a
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Nov 11, 2025
874ee82
[test] Notebook output
gabisponciano Nov 13, 2025
b98568c
Merge branch 'test/image-generation-notebook-output' of https://githu…
gabisponciano Nov 13, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
68 changes: 35 additions & 33 deletions generative-ai/image-generation-with-stablediffusion/notebooks/register-model.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-10-31 23:04:12 - INFO - Notebook execution started.\n"
"2025-11-13 15:43:02 - INFO - Notebook execution started.\n"
]
}
],
Expand Down Expand Up @@ -101,8 +101,8 @@
"output_type": "stream",
"text": [
"Note: you may need to restart the kernel to use updated packages.\n",
"CPU times: user 24.7 ms, sys: 3.97 ms, total: 28.7 ms\n",
"Wall time: 1.48 s\n"
"CPU times: user 145 ms, sys: 33.7 ms, total: 179 ms\n",
"Wall time: 5.46 s\n"
]
}
],
Expand All @@ -122,17 +122,19 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-10-31 23:04:18.497995: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
"2025-10-31 23:04:18.520479: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
"2025-11-13 15:43:15.497639: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
"2025-11-13 15:43:15.545453: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"E0000 00:00:1761951858.534689 1800 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
"E0000 00:00:1761951858.539003 1800 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"W0000 00:00:1761951858.550844 1800 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1761951858.550881 1800 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1761951858.550883 1800 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1761951858.550883 1800 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"2025-10-31 23:04:18.555210: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"E0000 00:00:1763048595.569621 1489 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
"E0000 00:00:1763048595.576553 1489 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"W0000 00:00:1763048595.604025 1489 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1763048595.604060 1489 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1763048595.604062 1489 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1763048595.604063 1489 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"2025-11-13 15:43:15.611536: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"W0000 00:00:1763048602.479530 1489 gpu_device.cc:2341] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n",
"Skipping registering GPU devices...\n",
"/opt/conda/lib/python3.12/site-packages/mlflow/pyfunc/utils/data_validation.py:137: FutureWarning: Model's `predict` method contains invalid parameters: {'X'}. Only the following parameter names are allowed: context, model_input, and params. Note that invalid parameters will no longer be permitted in future versions.\n",
" param_names = _check_func_signature(func, \"predict\")\n",
"/opt/conda/lib/python3.12/site-packages/mlflow/pyfunc/model.py:172: UserWarning: \u001b[31mType hint used in the model's predict function is not supported for MLflow's schema validation. Type hints must be wrapped in list[...] because MLflow assumes the predict method to take multiple input instances. Specify your type hint as `list[typing.Union[pandas.core.frame.DataFrame, dict]]` for a valid signature. Remove the type hint to disable this warning. To enable validation for the input data, specify input example or model signature when logging the model. \u001b[0m\n",
Expand Down Expand Up @@ -257,27 +259,27 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-10-31 23:04:26,613 — INFO — Using accelerate cfg: /home/jovyan/AI-Blueprints/generative-ai/image-generation-with-stablediffusion/configs/default_config_one-gpu.yaml\n",
"2025-10-31 23:04:26,932 — INFO — Starting model deployment...\n",
"2025/10/31 23:04:27 INFO mlflow.tracking.fluent: Experiment with name 'ImageGeneration' does not exist. Creating a new experiment.\n",
"2025-10-31 23:04:27,368 — INFO — Using local base model: /home/jovyan/AI-Blueprints/generative-ai/image-generation-with-stablediffusion/models/stable-diffusion-2-1\n",
"2025-10-31 23:04:27,371 — INFO — Using finetuned model: /home/jovyan/AI-Blueprints/generative-ai/image-generation-with-stablediffusion/output/dreambooth\n",
"2025-10-31 23:04:27,371 — INFO — Using base model: /home/jovyan/AI-Blueprints/generative-ai/image-generation-with-stablediffusion/models/stable-diffusion-2-1\n",
"2025-10-31 23:04:28,103 — INFO — 📦 Logging artifacts and model...\n",
"2025/10/31 23:04:28 INFO mlflow.models.signature: Inferring model signature from type hints\n",
"2025-11-13 15:43:29,426 — INFO — Using accelerate cfg: /home/jovyan/AI-Blueprints/generative-ai/image-generation-with-stablediffusion/configs/default_config_one-gpu.yaml\n",
"2025-11-13 15:43:29,730 — INFO — Starting model deployment...\n",
"2025/11/13 15:43:29 INFO mlflow.tracking.fluent: Experiment with name 'ImageGeneration' does not exist. Creating a new experiment.\n",
"2025-11-13 15:43:29,876 — INFO — Using local base model: /home/jovyan/AI-Blueprints/generative-ai/image-generation-with-stablediffusion/models/stable-diffusion-2-1\n",
"2025-11-13 15:43:29,881 — INFO — Using finetuned model: /home/jovyan/AI-Blueprints/generative-ai/image-generation-with-stablediffusion/output/dreambooth\n",
"2025-11-13 15:43:29,883 — INFO — Using base model: /home/jovyan/AI-Blueprints/generative-ai/image-generation-with-stablediffusion/models/stable-diffusion-2-1\n",
"2025-11-13 15:43:30,426 — INFO — 📦 Logging artifacts and model...\n",
"2025/11/13 15:43:30 INFO mlflow.models.signature: Inferring model signature from type hints\n",
"/opt/conda/lib/python3.12/site-packages/mlflow/pyfunc/__init__.py:3139: UserWarning: Failed to infer signature from type hint: Type hints must be wrapped in list[...] because MLflow assumes the predict method to take multiple input instances. Specify your type hint as `list[typing.Union[pandas.core.frame.DataFrame, dict]]` for a valid signature.\n",
" signature_from_type_hints = _infer_signature_from_type_hints(\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6b8ddc9bf7e6468492b5ec162d3c1261",
"model_id": "d3ac1d11139c4f17beff715473a6ee96",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading artifacts: 0%| | 0/16 [00:00<?, ?it/s]"
"Downloading artifacts: 0%| | 0/22 [00:00<?, ?it/s]"
]
},
"metadata": {},
Expand All @@ -286,7 +288,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e2abb95524c54435ada68df22671b1cd",
"model_id": "49137e65be394e08b3c2deadceb58d2b",
"version_major": 2,
"version_minor": 0
},
Expand All @@ -300,7 +302,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6711bc9d9d08450a82193b486cf42961",
"model_id": "7422cf131e0b4e309db5c43e64a92c06",
"version_major": 2,
"version_minor": 0
},
Expand All @@ -314,7 +316,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4012a7452b9e482eb53b7563b63097f7",
"model_id": "56bbb357fe374abfa499ae5059f4fd08",
"version_major": 2,
"version_minor": 0
},
Expand All @@ -329,19 +331,19 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-10-31 23:17:00,717 — INFO — ✅ Model logged to MLflow at 'image_generation_model'\n",
"2025-11-13 15:58:07,500 — INFO — ✅ Model logged to MLflow at 'image_generation_model'\n",
"Successfully registered model 'ImageGenerationService'.\n",
"Created version '1' of model 'ImageGenerationService'.\n",
"2025-10-31 23:17:01,255 — INFO — 🏷️ Registered 'ImageGenerationService' (run 35b643b5d5f44f858050a7c6d2bec769)\n",
"2025-10-31 23:17:01,256 — INFO — Model deployment completed successfully\n"
"2025-11-13 15:58:08,086 — INFO — 🏷️ Registered 'ImageGenerationService' (run 82f53001bae14f359bb462f01c3f87d6)\n",
"2025-11-13 15:58:08,087 — INFO — Model deployment completed successfully\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 2.17 s, sys: 1min 35s, total: 1min 37s\n",
"Wall time: 12min 35s\n"
"CPU times: user 3.58 s, sys: 2min 35s, total: 2min 38s\n",
"Wall time: 14min 39s\n"
]
}
],
Expand All @@ -360,8 +362,8 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-10-31 23:17:01 - INFO - ⏱️ Total execution time: 12m 48.75s\n",
"2025-10-31 23:17:01 - INFO - ✅ Notebook execution completed successfully.\n"
"2025-11-13 15:58:08 - INFO - ⏱️ Total execution time: 15m 5.31s\n",
"2025-11-13 15:58:08 - INFO - ✅ Notebook execution completed successfully.\n"
]
}
],
Expand Down
Loading