huggingface
diff --git a/‎.github/workflows/benchmark.yml
Lines changed: 1 addition & 0 deletions b/‎.github/workflows/benchmark.yml
Lines changed: 1 addition & 0 deletions
diff --git a/‎.github/workflows/nightly_tests.yml
Lines changed: 9 additions & 0 deletions b/‎.github/workflows/nightly_tests.yml
Lines changed: 9 additions & 0 deletions
diff --git a/‎.github/workflows/pr_tests_gpu.yml
Lines changed: 44 additions & 0 deletions b/‎.github/workflows/pr_tests_gpu.yml
Lines changed: 44 additions & 0 deletions
diff --git a/‎docs/source/en/_toctree.yml
Lines changed: 4 additions & 0 deletions b/‎docs/source/en/_toctree.yml
Lines changed: 4 additions & 0 deletions
diff --git a/‎docs/source/en/api/pipelines/ltx_video.md
Lines changed: 6 additions & 0 deletions b/‎docs/source/en/api/pipelines/ltx_video.md
Lines changed: 6 additions & 0 deletions
diff --git a/‎docs/source/en/api/pipelines/lumina.md
Lines changed: 7 additions & 7 deletions b/‎docs/source/en/api/pipelines/lumina.md
Lines changed: 7 additions & 7 deletions
diff --git a/‎docs/source/en/api/pipelines/lumina2.md
Lines changed: 6 additions & 6 deletions b/‎docs/source/en/api/pipelines/lumina2.md
Lines changed: 6 additions & 6 deletions
diff --git a/‎docs/source/en/api/pipelines/wan.md
Lines changed: 4 additions & 0 deletions b/‎docs/source/en/api/pipelines/wan.md
Lines changed: 4 additions & 0 deletions
diff --git a/‎docs/source/en/api/quantization.md
Lines changed: 5 additions & 0 deletions b/‎docs/source/en/api/quantization.md
Lines changed: 5 additions & 0 deletions
diff --git a/‎docs/source/en/hybrid_inference/api_reference.md
Lines changed: 4 additions & 0 deletions b/‎docs/source/en/hybrid_inference/api_reference.md
Lines changed: 4 additions & 0 deletions
diff --git a/‎docs/source/en/hybrid_inference/overview.md
Lines changed: 8 additions & 2 deletions b/‎docs/source/en/hybrid_inference/overview.md
Lines changed: 8 additions & 2 deletions
@@ -38,6 +38,7 @@ jobs:
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
           python -m uv pip install pandas peft
+          python -m uv pip uninstall transformers && python -m uv pip install transformers==4.48.0
       - name: Environment
         run: |
           python utils/print_env.py
 
@@ -414,10 +414,16 @@ jobs:
         config:
           - backend: "bitsandbytes"
             test_location: "bnb"
+            additional_deps: ["peft"]
           - backend: "gguf"
             test_location: "gguf"
+            additional_deps: []
           - backend: "torchao"
             test_location: "torchao"
+            additional_deps: []
+          - backend: "optimum_quanto"
+            test_location: "quanto"
+            additional_deps: []
     runs-on:
       group: aws-g6e-xlarge-plus
     container:
@@ -435,6 +441,9 @@ jobs:
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
           python -m uv pip install -U ${{ matrix.config.backend }}
+          if [ "${{ join(matrix.config.additional_deps, ' ') }}" != "" ]; then
+              python -m uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
+          fi
           python -m uv pip install pytest-reportlog
       - name: Environment
         run: |
 
@@ -28,7 +28,51 @@ env:
   PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run
 
 jobs:
+  check_code_quality:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check quality
+        run: make quality
+      - name: Check if failure
+        if: ${{ failure() }}
+        run: |
+          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
+
+  check_repository_consistency:
+    needs: check_code_quality
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check repo consistency
+        run: |
+          python utils/check_copies.py
+          python utils/check_dummies.py
+          python utils/check_support_list.py
+          make deps_table_check_updated
+      - name: Check if failure
+        if: ${{ failure() }}
+        run: |
+          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
+  
   setup_torch_cuda_pipeline_matrix:
+    needs: [check_code_quality, check_repository_consistency]
     name: Setup Torch Pipelines CUDA Slow Tests Matrix
     runs-on:
       group: aws-general-8-plus
 
@@ -81,6 +81,8 @@
     title: Overview
   - local: hybrid_inference/vae_decode
     title: VAE Decode
+  - local: hybrid_inference/vae_encode
+    title: VAE Encode
   - local: hybrid_inference/api_reference
     title: API Reference
   title: Hybrid Inference
@@ -173,6 +175,8 @@
     title: gguf
   - local: quantization/torchao
     title: torchao
+  - local: quantization/quanto 
+    title: quanto
   title: Quantization Methods
 - sections:
   - local: optimization/fp16
 
@@ -196,6 +196,12 @@ export_to_video(video, "ship.mp4", fps=24)
   - all
   - __call__
 
+## LTXConditionPipeline
+
+[[autodoc]] LTXConditionPipeline
+  - all
+  - __call__
+
 ## LTXPipelineOutput
 
 [[autodoc]] pipelines.ltx.pipeline_output.LTXPipelineOutput
@@ -58,10 +58,10 @@ Use [`torch.compile`](https://huggingface.co/docs/diffusers/main/en/tutorials/fa
 First, load the pipeline:
 
 ```python
-from diffusers import LuminaText2ImgPipeline
+from diffusers import LuminaPipeline
 import torch
 
-pipeline = LuminaText2ImgPipeline.from_pretrained(
+pipeline = LuminaPipeline.from_pretrained(
 	"Alpha-VLLM/Lumina-Next-SFT-diffusers", torch_dtype=torch.bfloat16
 ).to("cuda")
 ```
@@ -86,11 +86,11 @@ image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit w
 
 Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
 
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`LuminaText2ImgPipeline`] for inference with bitsandbytes.
+Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`LuminaPipeline`] for inference with bitsandbytes.
 
 ```py
 import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, Transformer2DModel, LuminaText2ImgPipeline
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, Transformer2DModel, LuminaPipeline
 from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
 
 quant_config = BitsAndBytesConfig(load_in_8bit=True)
@@ -109,7 +109,7 @@ transformer_8bit = Transformer2DModel.from_pretrained(
     torch_dtype=torch.float16,
 )
 
-pipeline = LuminaText2ImgPipeline.from_pretrained(
+pipeline = LuminaPipeline.from_pretrained(
     "Alpha-VLLM/Lumina-Next-SFT-diffusers",
     text_encoder=text_encoder_8bit,
     transformer=transformer_8bit,
@@ -122,9 +122,9 @@ image = pipeline(prompt).images[0]
 image.save("lumina.png")
 ```
 
-## LuminaText2ImgPipeline
+## LuminaPipeline
 
-[[autodoc]] LuminaText2ImgPipeline
+[[autodoc]] LuminaPipeline
 	- all
 	- __call__
 
@@ -36,14 +36,14 @@ Single file loading for Lumina Image 2.0 is available for the `Lumina2Transforme
 
 ```python
 import torch
-from diffusers import Lumina2Transformer2DModel, Lumina2Text2ImgPipeline
+from diffusers import Lumina2Transformer2DModel, Lumina2Pipeline
 
 ckpt_path = "https://huggingface.co/Alpha-VLLM/Lumina-Image-2.0/blob/main/consolidated.00-of-01.pth"
 transformer = Lumina2Transformer2DModel.from_single_file(
     ckpt_path, torch_dtype=torch.bfloat16
 )
 
-pipe = Lumina2Text2ImgPipeline.from_pretrained(
+pipe = Lumina2Pipeline.from_pretrained(
     "Alpha-VLLM/Lumina-Image-2.0", transformer=transformer, torch_dtype=torch.bfloat16
 )
 pipe.enable_model_cpu_offload()
@@ -60,7 +60,7 @@ image.save("lumina-single-file.png")
 GGUF Quantized checkpoints for the `Lumina2Transformer2DModel` can be loaded via `from_single_file` with the `GGUFQuantizationConfig` 
 
 ```python
-from diffusers import Lumina2Transformer2DModel, Lumina2Text2ImgPipeline, GGUFQuantizationConfig 
+from diffusers import Lumina2Transformer2DModel, Lumina2Pipeline, GGUFQuantizationConfig 
 
 ckpt_path = "https://huggingface.co/calcuis/lumina-gguf/blob/main/lumina2-q4_0.gguf"
 transformer = Lumina2Transformer2DModel.from_single_file(
@@ -69,7 +69,7 @@ transformer = Lumina2Transformer2DModel.from_single_file(
     torch_dtype=torch.bfloat16,
 )
 
-pipe = Lumina2Text2ImgPipeline.from_pretrained(
+pipe = Lumina2Pipeline.from_pretrained(
     "Alpha-VLLM/Lumina-Image-2.0", transformer=transformer, torch_dtype=torch.bfloat16
 )
 pipe.enable_model_cpu_offload()
@@ -80,8 +80,8 @@ image = pipe(
 image.save("lumina-gguf.png")
 ```
 
-## Lumina2Text2ImgPipeline
+## Lumina2Pipeline
 
-[[autodoc]] Lumina2Text2ImgPipeline
+[[autodoc]] Lumina2Pipeline
   - all
   - __call__
@@ -14,6 +14,10 @@
 
 # Wan
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 [Wan 2.1](https://github.com/Wan-Video/Wan2.1) by the Alibaba Wan Team.
 
 <!-- TODO(aryan): update abstract once paper is out -->
 
@@ -31,6 +31,11 @@ Learn how to quantize models in the [Quantization](../quantization/overview) gui
 ## GGUFQuantizationConfig
 
 [[autodoc]] GGUFQuantizationConfig
+
+## QuantoConfig
+
+[[autodoc]] QuantoConfig
+
 ## TorchAoConfig
 
 [[autodoc]] TorchAoConfig
 
@@ -3,3 +3,7 @@
 ## Remote Decode
 
 [[autodoc]] utils.remote_utils.remote_decode
+
+## Remote Encode
+
+[[autodoc]] utils.remote_utils.remote_encode
@@ -36,7 +36,7 @@ Hybrid Inference offers a fast and simple way to offload local generation requir
 ## Available Models
 
 * **VAE Decode 🖼️:** Quickly decode latent representations into high-quality images without compromising performance or workflow speed.
-* **VAE Encode 🔢 (coming soon):** Efficiently encode images into latent representations for generation and training.
+* **VAE Encode 🔢:** Efficiently encode images into latent representations for generation and training.
 * **Text Encoders 📃 (coming soon):** Compute text embeddings for your prompts quickly and accurately, ensuring a smooth and high-quality workflow.
 
 ---
@@ -46,9 +46,15 @@ Hybrid Inference offers a fast and simple way to offload local generation requir
 * **[SD.Next](https://github.com/vladmandic/sdnext):** All-in-one UI with direct supports Hybrid Inference.
 * **[ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae):** ComfyUI node for Hybrid Inference.
 
+## Changelog
+
+- March 10 2025: Added VAE encode
+- March 2 2025: Initial release with VAE decoding
+
 ## Contents
 
-The documentation is organized into two sections:
+The documentation is organized into three sections:
 
 * **VAE Decode** Learn the basics of how to use VAE Decode with Hybrid Inference.
+* **VAE Encode** Learn the basics of how to use VAE Encode with Hybrid Inference.
 * **API Reference** Dive into task-specific settings and parameters.