Add files using upload-large-folder tool

README.md

@@ -0,0 +1,135 @@
+---
+base_model:
+  - Wan-AI/Wan2.2-I2V-A14B
+base_model_relation: quantized
+pipeline_tag: image-to-video
+tags:
+- dfloat11
+- df11
+- lossless compression
+- 70% size, 100% accuracy
+---
+
+# DFloat11 Compressed Model: `Wan-AI/Wan2.2-I2V-A14B`
+
+This is a **DFloat11 losslessly compressed** version of the original `Wan-AI/Wan2.2-I2V-A14B` model. It reduces model size by **32%** compared to the original BFloat16 model, while maintaining **bit-identical outputs** and supporting **efficient GPU inference**.
+
+🔥🔥🔥 Thanks to DFloat11 compression, `Wan-AI/Wan2.2-I2V-A14B` can now generate a 5-second 720P video on a single 24GB GPU, while maintaining full model quality. 🔥🔥🔥
+
+### 📊 Performance Comparison
+
+| Model                                              | Model Size         | Peak GPU Memory (5-second 720P generation)   | Generation Time (A100 GPU) |
+|----------------------------------------------------|--------------------|----------------------------------------------|----------------------------|
+| Wan-AI/Wan2.2-I2V-A14B (BFloat16)                  | ~56 GB             | O.O.M.                                       | -                          |
+| Wan-AI/Wan2.2-I2V-A14B (DFloat11)                  | 19.47 + 19.44 GB   | 29.12 GB                                     | 42 minutes                 |
+| Wan-AI/Wan2.2-I2V-A14B (DFloat11 + CPU Offloading) | 19.47 + 19.44 GB   | 20.01 GB                                     | 44 minutes                 |
+
+### 🔍 How It Works
+
+We apply Huffman coding to the exponent bits of BFloat16 model weights, which are highly compressible. We leverage hardware-aware algorithmic designs to enable highly efficient, on-the-fly weight decompression directly on the GPU. Find out more in our [research paper](https://arxiv.org/abs/2504.11651).
+
+### 🔧 How to Use
+
+1. Install or upgrade the DFloat11 pip package *(installs the CUDA kernel automatically; requires a CUDA-compatible GPU and PyTorch installed)*:
+
+    ```bash
+    pip install -U dfloat11[cuda12]
+    ```
+
+2. Install the latest `diffusers` package from source:
+
+    ```bash
+    pip install git+https://github.com/huggingface/diffusers
+    ```
+
+3. Save the following code to a Python file `i2v.py`:
+
+    ```python
+    import time
+    import torch
+    import numpy as np
+    import argparse
+    from diffusers import WanImageToVideoPipeline
+    from diffusers.utils import export_to_video, load_image
+    from dfloat11 import DFloat11Model
+
+    parser = argparse.ArgumentParser(description='Image to Video generation using Wan2.2-I2V model')
+    parser.add_argument('--cpu_offload', action='store_true', help='Enable CPU offloading')
+    parser.add_argument('--image_path', type=str, default="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG", help='Path or URL to the input image')
+    parser.add_argument('--width', type=int, default=1280, help='Output video width')
+    parser.add_argument('--height', type=int, default=720, help='Output video height')
+    parser.add_argument('--prompt', type=str, default="Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside.", help='Prompt for video generation')
+    parser.add_argument('--negative_prompt', type=str, default="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走", help='Negative prompt for video generation')
+    parser.add_argument('--num_frames', type=int, default=81, help='Number of frames to generate')
+    parser.add_argument('--guidance_scale', type=float, default=3.5, help='Guidance scale for generation')
+    parser.add_argument('--num_inference_steps', type=int, default=40, help='Number of inference steps')
+    parser.add_argument('--seed', type=int, default=42, help='Random seed for generation')
+    parser.add_argument('--output', type=str, default='i2v_output.mp4', help='Output video path')
+    parser.add_argument('--fps', type=int, default=16, help='FPS of output video')
+
+    args = parser.parse_args()
+
+    image = load_image(args.image_path)
+
+    pipe = WanImageToVideoPipeline.from_pretrained("Wan-AI/Wan2.2-I2V-A14B-Diffusers", torch_dtype=torch.bfloat16)
+
+    DFloat11Model.from_pretrained(
+        "DFloat11/Wan2.2-I2V-A14B-DF11",
+        device="cpu",
+        cpu_offload=args.cpu_offload,
+        bfloat16_model=pipe.transformer,
+    )
+    DFloat11Model.from_pretrained(
+        "DFloat11/Wan2.2-I2V-A14B-2-DF11",
+        device="cpu",
+        cpu_offload=args.cpu_offload,
+        bfloat16_model=pipe.transformer_2,
+    )
+
+    pipe.enable_model_cpu_offload()
+
+    max_area = args.width * args.height
+    aspect_ratio = image.height / image.width
+    mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
+    height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
+    width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
+    image = image.resize((width, height))
+
+    generator = torch.Generator(device="cuda").manual_seed(args.seed)
+
+    start_time = time.time()
+    output = pipe(
+        image=image,
+        prompt=args.prompt,
+        negative_prompt=args.negative_prompt,
+        height=height,
+        width=width,
+        num_frames=args.num_frames,
+        guidance_scale=args.guidance_scale,
+        num_inference_steps=args.num_inference_steps,
+        generator=generator,
+    ).frames[0]
+    print(f"Time taken: {time.time() - start_time:.2f} seconds")
+
+    export_to_video(output, args.output, fps=args.fps)
+
+    max_memory = torch.cuda.max_memory_allocated()
+    print(f"Max memory: {max_memory / (1000 ** 3):.2f} GB")
+    ```
+
+4. To run without CPU offloading (40GB VRAM required):
+    ```bash
+    PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True python i2v.py
+    ```
+
+    To run with CPU offloading (22.5GB VRAM required):
+    ```bash
+    PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True python i2v.py --cpu_offload
+    ```
+    > Setting `PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True` is strongly recommended to prevent out-of-memory errors caused by GPU memory fragmentation.
+
+### 📄 Learn More
+
+* **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
+* **GitHub**: [https://github.com/LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
+* **HuggingFace**: [https://huggingface.co/DFloat11](https://huggingface.co/DFloat11)

blocks_0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a324342812eb85cf98a3bd867fccdbd92d293f4e1d8ebc2f6b6f4b8e2626eb
+size 473161015

blocks_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f40a05f5e8899facdbd3cffacae6b0d0c3ff4e45cea88139edfc1286a2f427
+size 474615568

blocks_10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542e7cfd87317225a0f628955aa146225dcf0d52eb8625b5023941aa10dcb1cf
+size 475484959

blocks_11.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ef65a6681b5154a0233d547053e12d72d9ddba34253cedbac0541cc5d9ae61
+size 475354524

blocks_12.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7de0a1bb344360953baac6c244584839135ebdeed0fd8c7956b962a2d0debc4
+size 475201326

blocks_13.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1843084fcc8f82006f39a3929c9ab8969517b95a316ac828abe32a4db59e1b2c
+size 474970332

blocks_14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541f9a07448449398f044e41aa500fc8bd1b75897f5c8ae918b0136d881be0c7
+size 474803606

blocks_15.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd42c00ea1c304ab70f0ba3d50537444737119dd5209134e582bfb548d3b7f8a
+size 474511914

blocks_16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa87cbe985b1831f7146cb0bd3dabc32c99095949f80187fbb06cf7b314800f
+size 474585500

blocks_17.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8449a37f3c42a9d8d35e19b67f17838b4b0f9c143c281d32c92121892f2b3f
+size 474372605

blocks_18.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9fde91610565a4fd9d7f59d296507f72438254ba136f11ce2fc91aa54c459
+size 474520915

blocks_19.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beac844d58d4003d4f842684dfca9e02cbac9b3d9a487b003c3cd841eb4cd51d
+size 474268282

blocks_2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032c3b05b6f44eea5a5fde21ee1b441f30e15280644e43b7b1b5859e64d1b9c8
+size 475042559

blocks_20.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efa432da6579c898b295787a6ed5a6b0fbe6b8dfb2926fc4774f9d7bda6decb
+size 474250749

blocks_21.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb4626b2adb82fc6f68b54bbf9ea6a557c1ee467d082fa947611678ee641aeb
+size 474239584

blocks_22.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e2b22362c635544e5da2742cdca1a16551b5a5befa8a36b7fa7cd034e7318e
+size 474057128

blocks_23.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b11221d6a8fca83f8cab8f39dccb1a7b6e0354e90fe85717305a2a3763a4b90
+size 473975556

blocks_24.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34a822c5bfeb5a9894ccb1e5c5467c95d1801688f008947e27b0cda13b0bf63
+size 473473196

blocks_25.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4cb530fd896c8ba643f780b954688429a534f14b6d13702f90bc9280420d84
+size 473201187

blocks_26.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0475225d686d0b8af0cfd5f43539f32aefbd68e67182f638eda8721cc8a4b3
+size 473077868

blocks_27.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57846a27bf2d7eb73662bb558ea5e2689a6f10a8bcf8aeb859f39ec6ff03c5de
+size 472957197

blocks_28.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1258cd8757f74b9b40ecdea72de672cd4883480d9be2aef09bf0f289e3309e15
+size 472806195

blocks_29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58138a1e5b7a0f01aacbb744377d2b8858a89101babeef341b774b6b95b2389f
+size 472543027

blocks_3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f5fa5d3d2effc9ef7ed99f0fb1f4315b905b44a8db7649d4284c1fae36eb9d
+size 475056015

blocks_30.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd7dd6b4fa8b688d1c157a88ae474e4801c0e7e3bc83a008f4b1a4e4d138c20
+size 472406322

blocks_31.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55886640cf56afb3d7506b175432b0dfb3df98ab0dc36567b32cb5f75aee129e
+size 472219358

blocks_32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ebf0958d2aa0f7ade67e6c64a38be0635938b0adeb66d28918f991dd417cd8
+size 471961135

blocks_33.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2211e0b13b0213f214bcd8260f69dfd19d5ea49a39d761101f2c1a65fbda86
+size 471359185

blocks_34.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f879542e12411988f43d4897308f76ba4b0a3e47ba290b258b478c62d26f4d9a
+size 471420534

blocks_35.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c7719457111bfe0008b14308e307796f1241c75f3debcb7fb79bae77c8628d
+size 471849658

blocks_36.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb159fb4320377c77f5307fc958229676e1a69c9eb19d839886360ec71f6e78
+size 471253989

blocks_37.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859a423dc9acb3ecbfaff5a57306b7b8a26598154556cadcdedcc9874146d7c8
+size 471159202

blocks_38.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69b2ee46b82b043984370823189c98c0cc377b7a5021ed91369219a9a3da82a
+size 470391601

blocks_39.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7d5343e8d22659a9ea58ef3ad65d7d477c6f41411115a8151aef7753e5d564
+size 470099464

blocks_4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711856613180b9e0fa6d608aa9fce7580cbe90846fff57c55cf519746f775847
+size 475013195

blocks_5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ca7fdafb35358aadd5e1bde151f0e19d1cf6f180362c4ba4c0f1c29941233e
+size 475082697

blocks_6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e1cc8dad9a3a559dc027af5cdf30dd14ba965abadf81e6f9b17ce6ecef3b0c
+size 475185086

blocks_7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e5f109a7e42ef4363f256def155c5be267118b3bd9b4423821f8357be07892
+size 475243387

blocks_8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd5c4572ef8c89b77413c710c9a9152f7783c4217c64f40870e90d50464ce71
+size 475350733

blocks_9.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f71960bdb37de9d109fdebbe8cad9c54f4b84158a9ae30c4385ec46863c2d35
+size 475554848

config.json

@@ -0,0 +1,24 @@
+{
+  "dfloat11_config": {
+    "bytes_per_thread": 8,
+    "pattern_dict": {
+      "blocks\\.\\d+": [
+        "attn1.to_q",
+        "attn1.to_k",
+        "attn1.to_v",
+        "attn1.to_out.0",
+        "attn2.to_q",
+        "attn2.to_k",
+        "attn2.to_v",
+        "attn2.to_out.0",
+        "ffn.net.0.proj",
+        "ffn.net.2"
+      ]
+    },
+    "threads_per_block": [
+      512
+    ],
+    "version": "0.3.1"
+  },
+  "model_type": "llama"
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fca4c76e97c2b346dc33466bac9da2b5eabf512dc7fa92a9655f84132c055ac
+size 521350912