add docker-slim

wolverinn · Jul 13, 2023 · 785c431 · 785c431
1 parent 9dfad6f
commit 785c431
Show file tree

Hide file tree

Showing 416 changed files with 76,899 additions and 8 deletions.
diff --git a/README.md b/README.md
@@ -146,11 +146,4 @@ If you don't want to deploy the load balancing server but still want to test the
 Finally, you can call your http API(test it using postman).
 
 # Part 2: Deploy using Runpod Serverless
-Check `handler.py` where I realized a demo handler for txt2img.
-
-deploy steps:
-- get a GPU server, download this repository and model files
-- install docker: https://docs.docker.com/engine/install/ubuntu/#set-up-the-repository
-- cd to the project directory(which contains `Dockerfile`)
-- docker build && docker tag && docker push (these are not bash commands!)
-- create serverless Endpoint on runpod: https://runpod.io?ref=bz40v32s
+see `sd-docker-slim`
diff --git a/sd-docker-slim/Dockerfile b/sd-docker-slim/Dockerfile
@@ -0,0 +1,37 @@
+FROM python:3.10-slim
+
+# install docker on ubuntu: https://docs.docker.com/engine/install/ubuntu/#set-up-the-repository
+# build image: docker build -t sd-multi .
+# docker image ls
+# dockerhub create repo
+# login on ubuntu: docker login
+# tag: docker tag sd-multi wolverinn/sd_multi_demo:v1
+# push: docker push wolverinn/sd_multi_demo:v1
+
+WORKDIR /
+
+COPY requirements.txt /
+# COPY torch-1.13.1+cu117-cp38-cp38-linux_x86_64.whl .
+
+RUN apt-get update && apt-get install -y libgl1-mesa-glx  && \
+    apt-get install -y libglib2.0-0 && \
+    apt-get install -y git && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN pip3 install runpod==0.9.12 && \
+    pip3 install -r requirements.txt && \
+    # pip3 install torch-1.13.1+cu117-cp38-cp38-linux_x86_64.whl && \
+    pip3 install torch==1.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117 && \
+    pip3 install torchvision==0.14.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117 && \
+    # apt-get remove -y git && \
+    # rm -rf torch-1.13.1+cu117-cp38-cp38-linux_x86_64.whl && \
+    pip3 cache purge
+
+COPY . /
+RUN chmod +x docker_entrypoint.sh
+
+# COPY . /
+
+ENTRYPOINT ["/docker_entrypoint.sh"]
+
+CMD [ "python", "-u", "/handler.py" ]
diff --git a/sd-docker-slim/README.md b/sd-docker-slim/README.md
@@ -0,0 +1,39 @@
+# stable-diffusion docker slim
+
+# Features
+
+- deploy on runpod serverless
+- text2img, img2img, list models
+- upload models at any time, takes effect immediately
+
+# Deploy Steps
+
+## Build and upload docker
+- get a Ubuntu machine with GPU, download the project files
+- install docker on ubuntu: https://docs.docker.com/engine/install/ubuntu/#set-up-the-repository
+- cd to the directory with `Dockerfile`
+    - to make your custom docker, modify `handler.py` for uploading outputs & supporting more API ...
+- `docker build -t sd-multi .`
+- `docker login`
+- docker tag and then docker push
+
+## Create a storage on runpod
+- upload model files to storage volume. under `/workspace` you should upload the whole `models` directory. The directory structure should look like this:
+
+```
+/workspace
+    - /models
+        - /VAE
+        - /Lora
+        - /Stable-diffusion
+        ...
+```
+
+## Deploy on runpod serverless
+check the official guide: https://docs.runpod.io/docs/template-creation
+
+# Test your API
+check out `test_runpod.py`
+
+## API definition
+checkout `idl.yaml`
diff --git a/sd-docker-slim/config.json b/sd-docker-slim/config.json
@@ -0,0 +1,146 @@
+{
+    "samples_save": true,
+    "samples_format": "png",
+    "samples_filename_pattern": "",
+    "save_images_add_number": true,
+    "grid_save": true,
+    "grid_format": "png",
+    "grid_extended_filename": false,
+    "grid_only_if_multiple": true,
+    "grid_prevent_empty_spots": false,
+    "n_rows": -1,
+    "enable_pnginfo": true,
+    "save_txt": false,
+    "save_images_before_face_restoration": false,
+    "save_images_before_highres_fix": false,
+    "save_images_before_color_correction": false,
+    "jpeg_quality": 80,
+    "export_for_4chan": true,
+    "img_downscale_threshold": 4.0,
+    "target_side_length": 4000,
+    "use_original_name_batch": true,
+    "use_upscaler_name_as_suffix": false,
+    "save_selected_only": true,
+    "do_not_add_watermark": false,
+    "temp_dir": "",
+    "clean_temp_dir_at_start": false,
+    "outdir_samples": "",
+    "outdir_txt2img_samples": "outputs/txt2img-images",
+    "outdir_img2img_samples": "outputs/img2img-images",
+    "outdir_extras_samples": "outputs/extras-images",
+    "outdir_grids": "",
+    "outdir_txt2img_grids": "outputs/txt2img-grids",
+    "outdir_img2img_grids": "outputs/img2img-grids",
+    "outdir_save": "log/images",
+    "save_to_dirs": true,
+    "grid_save_to_dirs": true,
+    "use_save_to_dirs_for_ui": false,
+    "directories_filename_pattern": "[date]",
+    "directories_max_prompt_words": 8,
+    "ESRGAN_tile": 192,
+    "ESRGAN_tile_overlap": 8,
+    "realesrgan_enabled_models": [
+        "R-ESRGAN 4x+",
+        "R-ESRGAN 4x+ Anime6B"
+    ],
+    "upscaler_for_img2img": null,
+    "face_restoration_model": "CodeFormer",
+    "code_former_weight": 0.5,
+    "face_restoration_unload": false,
+    "show_warnings": false,
+    "memmon_poll_rate": 8,
+    "samples_log_stdout": false,
+    "multiple_tqdm": true,
+    "print_hypernet_extra": false,
+    "unload_models_when_training": false,
+    "pin_memory": false,
+    "save_optimizer_state": false,
+    "save_training_settings_to_txt": true,
+    "dataset_filename_word_regex": "",
+    "dataset_filename_join_string": " ",
+    "training_image_repeats_per_epoch": 1,
+    "training_write_csv_every": 500,
+    "training_xattention_optimizations": false,
+    "training_enable_tensorboard": false,
+    "training_tensorboard_save_images": false,
+    "training_tensorboard_flush_every": 120,
+    "sd_checkpoint_cache": 0,
+    "sd_vae_checkpoint_cache": 0,
+    "sd_vae": "Automatic",
+    "sd_vae_as_default": true,
+    "inpainting_mask_weight": 1.0,
+    "initial_noise_multiplier": 1.0,
+    "img2img_color_correction": false,
+    "img2img_fix_steps": false,
+    "img2img_background_color": "#ffffff",
+    "enable_quantization": false,
+    "enable_emphasis": true,
+    "enable_batch_seeds": true,
+    "comma_padding_backtrack": 20,
+    "CLIP_stop_at_last_layers": 1,
+    "upcast_attn": false,
+    "use_old_emphasis_implementation": false,
+    "use_old_karras_scheduler_sigmas": false,
+    "no_dpmpp_sde_batch_determinism": false,
+    "use_old_hires_fix_width_height": false,
+    "interrogate_keep_models_in_memory": false,
+    "interrogate_return_ranks": false,
+    "interrogate_clip_num_beams": 1,
+    "interrogate_clip_min_length": 24,
+    "interrogate_clip_max_length": 48,
+    "interrogate_clip_dict_limit": 1500,
+    "interrogate_clip_skip_categories": [],
+    "interrogate_deepbooru_score_threshold": 0.5,
+    "deepbooru_sort_alpha": true,
+    "deepbooru_use_spaces": false,
+    "deepbooru_escape": true,
+    "deepbooru_filter_tags": "",
+    "extra_networks_default_view": "cards",
+    "extra_networks_default_multiplier": 1.0,
+    "sd_hypernetwork": "None",
+    "return_grid": true,
+    "do_not_show_images": false,
+    "add_model_hash_to_info": true,
+    "add_model_name_to_info": true,
+    "disable_weights_auto_swap": true,
+    "send_seed": true,
+    "send_size": true,
+    "font": "",
+    "js_modal_lightbox": true,
+    "js_modal_lightbox_initially_zoomed": true,
+    "show_progress_in_title": true,
+    "samplers_in_dropdown": true,
+    "dimensions_and_batch_together": true,
+    "keyedit_precision_attention": 0.1,
+    "keyedit_precision_extra": 0.05,
+    "quicksettings": "sd_model_checkpoint",
+    "ui_reorder": "inpaint, sampler, checkboxes, hires_fix, dimensions, cfg, seed, batch, override_settings, scripts",
+    "ui_extra_networks_tab_reorder": "",
+    "localization": "zh_CN",
+    "show_progressbar": true,
+    "live_previews_enable": true,
+    "show_progress_grid": true,
+    "show_progress_every_n_steps": 10,
+    "show_progress_type": "Approx NN",
+    "live_preview_content": "Prompt",
+    "live_preview_refresh_period": 1000,
+    "hide_samplers": [],
+    "eta_ddim": 0.0,
+    "eta_ancestral": 1.0,
+    "ddim_discretize": "uniform",
+    "s_churn": 0.0,
+    "s_tmin": 0.0,
+    "s_noise": 1.0,
+    "eta_noise_seed_delta": 0,
+    "always_discard_next_to_last_sigma": false,
+    "postprocessing_enable_in_main_ui": [],
+    "postprocessing_operation_order": [],
+    "upscaling_max_images_in_cache": 5,
+    "disabled_extensions": [],
+    "ldsr_steps": 100,
+    "ldsr_cached": false,
+    "SWIN_tile": 192,
+    "SWIN_tile_overlap": 8,
+    "sd_lora": "None",
+    "lora_apply_to_outputs": false
+}
diff --git a/sd-docker-slim/configs/alt-diffusion-inference.yaml b/sd-docker-slim/configs/alt-diffusion-inference.yaml
@@ -0,0 +1,72 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: modules.xlmr.BertSeriesModelWithTransformation
+      params:
+        name: "XLMR-Large"