1.11.2

.github/workflows/tests.yaml

@@ -0,0 +1,119 @@
+name: Run AnimateDiff generation with Motion LoRA & Prompt Travel on CPU
+
+on:
+  push: {}  # Remove the branch restriction to trigger the workflow for any branch
+
+jobs:
+  build:
+    runs-on: ubuntu-20.04
+    steps:
+      - name: Checkout A1111
+        uses: actions/checkout@v3
+        with:
+          repository: 'AUTOMATIC1111/stable-diffusion-webui'
+          path: 'stable-diffusion-webui'
+      - name: Checkout ControlNet
+        uses: actions/checkout@v3
+        with:
+          repository: 'Mikubill/sd-webui-controlnet'
+          path: 'stable-diffusion-webui/extensions/sd-webui-controlnet'
+      - name: Checkout AnimateDiff
+        uses: actions/checkout@v3
+        with:
+          repository: 'continue-revolution/sd-webui-animatediff'
+          path: 'stable-diffusion-webui/extensions/sd-webui-animatediff'
+      - name: Set up Python 3.11.4
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11.4
+          cache: pip
+          cache-dependency-path: |
+            **/requirements*txt
+            launch.py
+      - name: Install test dependencies
+        run: |
+          pip install wait-for-it
+          pip install -r requirements-test.txt
+        working-directory: stable-diffusion-webui
+        env:
+          PIP_DISABLE_PIP_VERSION_CHECK: "1"
+          PIP_PROGRESS_BAR: "off"
+      - name: Setup environment
+        run: python launch.py --skip-torch-cuda-test --exit
+        working-directory: stable-diffusion-webui
+        env:
+          PIP_DISABLE_PIP_VERSION_CHECK: "1"
+          PIP_PROGRESS_BAR: "off"
+          TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu
+          WEBUI_LAUNCH_LIVE_OUTPUT: "1"
+          PYTHONUNBUFFERED: "1"
+      - name: Cache AnimateDiff models
+        uses: actions/cache@v3
+        with:
+          path: stable-diffusion-webui/extensions/sd-webui-animatediff/model/
+          key: animatediff-models-v1
+      - name: Cache LoRA models
+        uses: actions/cache@v3
+        with:
+          path: stable-diffusion-webui/models/Lora
+          key: lora-models-v1
+      - name: Download AnimateDiff model for testing
+        run: |
+          if [ ! -f "extensions/sd-webui-animatediff/model/mm_sd_v15_v2.ckpt" ]; then
+            curl -Lo extensions/sd-webui-animatediff/model/mm_sd_v15_v2.ckpt https://huggingface.co/guoyww/animatediff/resolve/main/mm_sd_v15_v2.ckpt?download=true
+          fi
+        working-directory: stable-diffusion-webui
+      - name: Download LoRA model for testing
+        run: |
+          if [ ! -d "models/Lora" ]; then
+            mkdir models/Lora
+          fi
+          if [ ! -f "models/Lora/yoimiya.safetensors" ]; then
+            curl -Lo models/Lora/yoimiya.safetensors https://civitai.com/api/download/models/48374?type=Model&format=SafeTensor
+          fi
+          if [ ! -f "models/Lora/v2_lora_TiltDown.ckpt" ]; then
+            curl -Lo models/Lora/v2_lora_TiltDown.ckpt https://huggingface.co/guoyww/animatediff/resolve/main/v2_lora_TiltDown.ckpt?download=true
+          fi
+        working-directory: stable-diffusion-webui
+      - name: Start test server
+        run: >
+          python -m coverage run
+          --data-file=.coverage.server
+          launch.py
+          --skip-prepare-environment
+          --skip-torch-cuda-test
+          --test-server
+          --do-not-download-clip
+          --no-half
+          --disable-opt-split-attention
+          --use-cpu all
+          --api-server-stop
+          2>&1 | tee output.txt &
+        working-directory: stable-diffusion-webui
+      - name: Run tests
+        run: |
+          wait-for-it --service 127.0.0.1:7860 -t 600
+          python -m pytest -vv --junitxml=test/results.xml --cov ./extensions/sd-webui-animatediff --cov-report=xml --verify-base-url ./extensions/sd-webui-animatediff/tests
+        working-directory: stable-diffusion-webui
+      - name: Kill test server
+        if: always()
+        run: curl -vv -XPOST http://127.0.0.1:7860/sdapi/v1/server-stop && sleep 10
+      - name: Show coverage
+        run: |
+          python -m coverage combine .coverage*
+          python -m coverage report -i
+          python -m coverage html -i
+        working-directory: stable-diffusion-webui
+      - name: Upload main app output
+        uses: actions/upload-artifact@v3
+        if: always()
+        with:
+          name: output
+          path: output.txt
+      - name: Upload coverage HTML
+        uses: actions/upload-artifact@v3
+        if: always()
+        with:
+          name: htmlcov
+          path: htmlcov
+

README.md

@@ -53,7 +53,7 @@ You might also be interested in another extension I created: [Segment Anything f
 - `2023/10/21`: [v1.9.4](https://github.com/continue-revolution/sd-webui-animatediff/releases/tag/v1.9.4): Save prompt travel to output images, `Reverse` merged to `Closed loop` (See [WebUI Parameters](#webui-parameters)), remove `TimestepEmbedSequential` hijack, remove `hints.js`, better explanation of several context-related parameters.
 - `2023/10/25`: [v1.10.0](https://github.com/continue-revolution/sd-webui-animatediff/releases/tag/v1.10.0): Support img2img batch. You need ControlNet installed to make it work properly (you do not need to enable ControlNet). See [ControlNet V2V](#controlnet-v2v) for more information.
 - `2023/10/29`: [v1.11.0](https://github.com/continue-revolution/sd-webui-animatediff/releases/tag/v1.11.0): Support [HotShot-XL](https://github.com/hotshotco/Hotshot-XL) for SDXL. See [HotShot-XL](#hotshot-xl) for more information.
-- `2023/11/06`: [v1.11.1](https://github.com/continue-revolution/sd-webui-animatediff/releases/tag/v1.11.1): optimize VRAM to support any number of control images for ControlNet V2V, patch [encode_pil_to_base64](https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/modules/api/api.py#L104-L133) to support api return a video, save frames to `AnimateDIff/yy-mm-dd/`, recover from assertion error without restart.
+- `2023/11/06`: [v1.11.1](https://github.com/continue-revolution/sd-webui-animatediff/releases/tag/v1.11.1): optimize VRAM for ControlNet V2V, patch [encode_pil_to_base64](https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/modules/api/api.py#L104-L133) for api return a video, save frames to `AnimateDIff/yy-mm-dd/`, recover from assertion error, test case, optional [request id](#api) for API.
 
 For future update plan, please query [here](https://github.com/continue-revolution/sd-webui-animatediff/pull/224).
 
@@ -94,7 +94,8 @@ It is quite similar to the way you use ControlNet. API will return a video in ba
       'latent_scale': 32,     # Latent scale
       'last_frame': None,     # Optional last frame
       'latent_power_last': 1, # Optional latent power for last frame
-      'latent_scale_last': 32 # Optional latent scale for last frame
+      'latent_scale_last': 32,# Optional latent scale for last frame
+      'request_id': ''        # Optional request id. If provided, outputs will have request id as filename suffix
       }
     ]
   }

scripts/animatediff_infv2v.py

@@ -111,12 +111,12 @@ def mm_cn_select(context: List[int]):
                         if control.hint_cond.shape[0] > len(context):
                             control.hint_cond_backup = control.hint_cond
                             control.hint_cond = control.hint_cond[context]
-                        control.hint_cond = control.hint_cond.to(device=shared.device)
+                        control.hint_cond = control.hint_cond.to(device=devices.get_device_for("controlnet"))
                         if control.hr_hint_cond is not None:
                             if control.hr_hint_cond.shape[0] > len(context):
                                 control.hr_hint_cond_backup = control.hr_hint_cond
                                 control.hr_hint_cond = control.hr_hint_cond[context]
-                            control.hr_hint_cond = control.hr_hint_cond.to(device=shared.device)
+                            control.hr_hint_cond = control.hr_hint_cond.to(device=devices.get_device_for("controlnet"))
                     # IPAdapter and Controlllite are always on CPU.
                     elif control.control_model_type == ControlModelType.IPAdapter and control.control_model.image_emb.shape[0] > len(context):
                         control.control_model.image_emb_backup = control.control_model.image_emb

scripts/animatediff_output.py

@@ -31,7 +31,9 @@ def output(self, p: StableDiffusionProcessing, res: Processed, params: AnimateDi
             frame_list = [image.copy() for image in res.images[i : i + params.video_length]]
 
             seq = images.get_next_sequence_number(output_dir, "")
-            filename = f"{seq:05}-{res.all_seeds[(i-res.index_of_first_image)]}"
+            filename_suffix = f"-{params.request_id}" if params.request_id else ""
+            filename = f"{seq:05}-{res.all_seeds[(i-res.index_of_first_image)]}{filename_suffix}"
+
             video_path_prefix = output_dir / filename
 
             frame_list = self._add_reverse(params, frame_list)

scripts/animatediff_ui.py

@@ -44,6 +44,7 @@ def __init__(
         last_frame=None,
         latent_power_last=1,
         latent_scale_last=32,
+        request_id = '',
     ):
         self.model = model
         self.enable = enable
@@ -64,10 +65,11 @@ def __init__(
         self.last_frame = last_frame
         self.latent_power_last = latent_power_last
         self.latent_scale_last = latent_scale_last
+        self.request_id = request_id
 
 
     def get_list(self, is_img2img: bool):
-        list_var = list(vars(self).values())
+        list_var = list(vars(self).values())[:-1]
         if is_img2img:
             animatediff_i2ibatch.hack()
         else:
@@ -89,6 +91,8 @@ def get_dict(self, is_img2img: bool):
             "interp": self.interp,
             "interp_x": self.interp_x,
         }
+        if self.request_id:
+            infotext['request_id'] = self.request_id
         if motion_module.mm is not None and motion_module.mm.mm_hash is not None:
             infotext['mm_hash'] = motion_module.mm.mm_hash[:8]
         if is_img2img:

tests/test_simple.py

@@ -0,0 +1,63 @@
+
+import pytest
+import requests
+
+
+@pytest.fixture()
+def url_txt2img(base_url):
+    return f"{base_url}/sdapi/v1/txt2img"
+
+
+@pytest.fixture()
+def error_txt2img_request():
+    return {
+        "prompt": '1girl, yoimiya (genshin impact), origen, line, comet, wink, Masterpiece, BestQuality. UltraDetailed, <lora:yoimiya:0.8>, <lora:v2_lora_TiltDown:0.8>\n0: closed mouth\n8: open mouth,',
+        "negative_prompt": "(sketch, duplicate, ugly, huge eyes, text, logo, monochrome, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt_v2, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), crown braid, ((2girl)), (deformed fingers:1.2), (long fingers:1.2),succubus wings,horn,succubus horn,succubus hairstyle, (bad-artist-anime), bad-artist, bad hand, grayscale, skin spots, acnes, skin blemishes",
+        "batch_size": 1,
+        "steps": 1,
+        "cfg_scale": 7,
+        "alwayson_scripts": {
+            'AnimateDiff': {
+                'args': [{
+                    'enable': True,
+                    'batch_size': 1,
+                    'video_length': 2,
+                }]
+            }
+        }
+    }
+
+
+@pytest.fixture()
+def correct_txt2img_request():
+    return {
+        "prompt": '1girl, yoimiya (genshin impact), origen, line, comet, wink, Masterpiece, BestQuality. UltraDetailed, <lora:yoimiya:0.8>, <lora:v2_lora_TiltDown:0.8>\n0: closed mouth\n1: open mouth,',
+        "negative_prompt": "(sketch, duplicate, ugly, huge eyes, text, logo, monochrome, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt_v2, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), crown braid, ((2girl)), (deformed fingers:1.2), (long fingers:1.2),succubus wings,horn,succubus horn,succubus hairstyle, (bad-artist-anime), bad-artist, bad hand, grayscale, skin spots, acnes, skin blemishes",
+        "batch_size": 1,
+        "steps": 1,
+        "cfg_scale": 7,
+        "alwayson_scripts": {
+            'AnimateDiff': {
+                'args': [{
+                    'enable': True,
+                    'batch_size': 1,
+                    'video_length': 2,
+                }]
+            }
+        }
+    }
+
+
+def test_txt2img_simple_performed(url_txt2img, error_txt2img_request, correct_txt2img_request):
+    '''
+    This test checks the following:
+    - simple t2v generation
+    - prompt travel
+    - infinite context generator
+    - motion lora
+    - error recovery
+    '''
+    assert requests.post(url_txt2img, json=error_txt2img_request).status_code == 500
+    response = requests.post(url_txt2img, json=correct_txt2img_request)
+    assert response.status_code == 200
+    assert isinstance(response.json()['images'][0], str)