diffsynth 1.1.1__tar.gz → 1.1.3__tar.gz

{diffsynth-1.1.1 → diffsynth-1.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: diffsynth
-Version: 1.1.1
+Version: 1.1.3
 Summary: Enjoy the magic of Diffusion models!
 Author: Artiprocher
 Classifier: Programming Language :: Python :: 3

{diffsynth-1.1.1 → diffsynth-1.1.3}/README.md

@@ -13,11 +13,19 @@ Document: https://diffsynth-studio.readthedocs.io/zh-cn/latest/index.html
 
 ## Introduction
 
-DiffSynth Studio is a Diffusion engine. We have restructured architectures including Text Encoder, UNet, VAE, among others, maintaining compatibility with models from the open-source community while enhancing computational performance. We provide many interesting features. Enjoy the magic of Diffusion models!
+Welcome to the magic world of Diffusion models!
 
-Until now, DiffSynth Studio has supported the following models:
+DiffSynth consists of two open-source projects:
+* [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio): Focused on aggressive technological exploration. Targeted at academia. Provides more cutting-edge technical support and novel inference capabilities.
+* [DiffSynth-Engine](https://github.com/modelscope/DiffSynth-Engine): Focused on stable model deployment. Geared towards industry. Offers better engineering support, higher computational performance, and more stable functionality.
 
-* [HunyuanVideo](https://github.com/Tencent/HunyuanVideo)
+DiffSynth-Studio is an open-source project aimed at exploring innovations in AIGC technology. We have integrated numerous open-source Diffusion models, including FLUX and Wan, among others. Through this open-source project, we hope to connect models within the open-source community and explore new technologies based on diffusion models.
+
+Until now, DiffSynth-Studio has supported the following models:
+
+* [Wan-Video](https://github.com/Wan-Video/Wan2.1)
+* [StepVideo](https://github.com/stepfun-ai/Step-Video-T2V)
+* [HunyuanVideo](https://github.com/Tencent/HunyuanVideo), [HunyuanVideo-I2V]()
 * [CogVideoX](https://huggingface.co/THUDM/CogVideoX-5b)
 * [FLUX](https://huggingface.co/black-forest-labs/FLUX.1-dev)
 * [ExVideo](https://huggingface.co/ECNU-CILab/ExVideo-SVD-128f-v1)
@@ -34,11 +42,21 @@ Until now, DiffSynth Studio has supported the following models:
 * [Stable Diffusion](https://huggingface.co/runwayml/stable-diffusion-v1-5)
 
 ## News
+- **March 31, 2025** We support InfiniteYou, an identity preserving method for FLUX. Please refer to [./examples/InfiniteYou/](./examples/InfiniteYou/) for more details.
+
+- **March 25, 2025** 🔥🔥🔥 Our new open-source project, [DiffSynth-Engine](https://github.com/modelscope/DiffSynth-Engine), is now open-sourced! Focused on stable model deployment. Geared towards industry. Offers better engineering support, higher computational performance, and more stable functionality.
+
+- **March 13, 2025** We support HunyuanVideo-I2V, the image-to-video generation version of HunyuanVideo open-sourced by Tencent. Please refer to [./examples/HunyuanVideo/](./examples/HunyuanVideo/) for more details.
+
+- **February 25, 2025** We support Wan-Video, a collection of SOTA video synthesis models open-sourced by Alibaba. See [./examples/wanvideo/](./examples/wanvideo/).
+
+- **February 17, 2025** We support [StepVideo](https://modelscope.cn/models/stepfun-ai/stepvideo-t2v/summary)! State-of-the-art video synthesis model! See [./examples/stepvideo](./examples/stepvideo/).
+
 - **December 31, 2024** We propose EliGen, a novel framework for precise entity-level controlled text-to-image generation, complemented by an inpainting fusion pipeline to extend its capabilities to image inpainting tasks. EliGen seamlessly integrates with existing community models, such as IP-Adapter and In-Context LoRA, enhancing its versatility. For more details, see [./examples/EntityControl](./examples/EntityControl/).
-  * Paper: [EliGen: Entity-Level Controlled Image Generation with Regional Attention](https://arxiv.org/abs/2501.01097)
-  * Github: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
-  * Model: [ModelScope](https://www.modelscope.cn/models/DiffSynth-Studio/Eligen)
-  * Training dataset: Coming soon
+  - Paper: [EliGen: Entity-Level Controlled Image Generation with Regional Attention](https://arxiv.org/abs/2501.01097)
+  - Model: [ModelScope](https://www.modelscope.cn/models/DiffSynth-Studio/Eligen), [HuggingFace](https://huggingface.co/modelscope/EliGen)
+  - Online Demo: [ModelScope EliGen Studio](https://www.modelscope.cn/studios/DiffSynth-Studio/EliGen)
+  - Training Dataset: [EliGen Train Set](https://www.modelscope.cn/datasets/DiffSynth-Studio/EliGenTrainSet)
 
 - **December 19, 2024** We implement advanced VRAM management for HunyuanVideo, making it possible to generate videos at a resolution of 129x720x1280 using 24GB of VRAM, or at 129x512x384 resolution with just 6GB of VRAM. Please refer to [./examples/HunyuanVideo/](./examples/HunyuanVideo/) for more details.
 
@@ -65,7 +83,7 @@ Until now, DiffSynth Studio has supported the following models:
   - Enable CFG and highres-fix to improve visual quality. See [here](/examples/image_synthesis/README.md)
   - LoRA, ControlNet, and additional models will be available soon.
 
-- **June 21, 2024.** 🔥🔥🔥 We propose ExVideo, a post-tuning technique aimed at enhancing the capability of video generation models. We have extended Stable Video Diffusion to achieve the generation of long videos up to 128 frames.
+- **June 21, 2024.** We propose ExVideo, a post-tuning technique aimed at enhancing the capability of video generation models. We have extended Stable Video Diffusion to achieve the generation of long videos up to 128 frames.
   - [Project Page](https://ecnu-cilab.github.io/ExVideoProjectPage/)
   - Source code is released in this repo. See [`examples/ExVideo`](./examples/ExVideo/).
   - Models are released on [HuggingFace](https://huggingface.co/ECNU-CILab/ExVideo-SVD-128f-v1) and [ModelScope](https://modelscope.cn/models/ECNU-CILab/ExVideo-SVD-128f-v1).
@@ -114,12 +132,19 @@ cd DiffSynth-Studio
 pip install -e .
 ```
 
-Or install from pypi:
+Or install from pypi (There is a delay in the update. If you want to experience the latest features, please do not use this installation method.):
 
 ```
 pip install diffsynth
 ```
 
+If you encounter issues during installation, it may be caused by the packages we depend on. Please refer to the documentation of the package that caused the problem.
+
+* [torch](https://pytorch.org/get-started/locally/)
+* [sentencepiece](https://github.com/google/sentencepiece)
+* [cmake](https://cmake.org)
+* [cupy](https://docs.cupy.dev/en/stable/install.html)
+
 ## Usage (in Python code)
 
 The Python examples are in [`examples`](./examples/). We provide an overview here.

{diffsynth-1.1.1 → diffsynth-1.1.3}/diffsynth/configs/model_config.py

@@ -37,6 +37,7 @@ from ..models.flux_text_encoder import FluxTextEncoder2
 from ..models.flux_vae import FluxVAEEncoder, FluxVAEDecoder
 from ..models.flux_controlnet import FluxControlNet
 from ..models.flux_ipadapter import FluxIpAdapter
+from ..models.flux_infiniteyou import InfiniteYouImageProjector
 
 from ..models.cog_vae import CogVAEEncoder, CogVAEDecoder
 from ..models.cog_dit import CogDiT
@@ -51,6 +52,14 @@ from ..extensions.ESRGAN import RRDBNet
 
 from ..models.hunyuan_video_dit import HunyuanVideoDiT
 
+from ..models.stepvideo_vae import StepVideoVAE
+from ..models.stepvideo_dit import StepVideoModel
+
+from ..models.wan_video_dit import WanModel
+from ..models.wan_video_text_encoder import WanTextEncoder
+from ..models.wan_video_image_encoder import WanImageEncoder
+from ..models.wan_video_vae import WanVideoVAE
+
 
 model_loader_configs = [
     # These configs are provided for detecting model type automatically.
@@ -87,6 +96,7 @@ model_loader_configs = [
     (None, "57b02550baab820169365b3ee3afa2c9", ["flux_dit"], [FluxDiT], "civitai"),
     (None, "3394f306c4cbf04334b712bf5aaed95f", ["flux_dit"], [FluxDiT], "civitai"),
     (None, "023f054d918a84ccf503481fd1e3379e", ["flux_dit"], [FluxDiT], "civitai"),
+    (None, "605c56eab23e9e2af863ad8f0813a25d", ["flux_dit"], [FluxDiT], "diffusers"),
     (None, "280189ee084bca10f70907bf6ce1649d", ["cog_vae_encoder", "cog_vae_decoder"], [CogVAEEncoder, CogVAEDecoder], "diffusers"),
     (None, "9b9313d104ac4df27991352fec013fd4", ["rife"], [IFNet], "civitai"),
     (None, "6b7116078c4170bfbeaedc8fe71f6649", ["esrgan"], [RRDBNet], "civitai"),
@@ -95,6 +105,8 @@ model_loader_configs = [
     (None, "b001c89139b5f053c715fe772362dd2a", ["flux_controlnet"], [FluxControlNet], "diffusers"),
     (None, "52357cb26250681367488a8954c271e8", ["flux_controlnet"], [FluxControlNet], "diffusers"),
     (None, "0cfd1740758423a2a854d67c136d1e8c", ["flux_controlnet"], [FluxControlNet], "diffusers"),
+    (None, "7f9583eb8ba86642abb9a21a4b2c9e16", ["flux_controlnet"], [FluxControlNet], "diffusers"),
+    (None, "c07c0f04f5ff55e86b4e937c7a40d481", ["infiniteyou_image_projector"], [InfiniteYouImageProjector], "diffusers"),
     (None, "4daaa66cc656a8fe369908693dad0a35", ["flux_ipadapter"], [FluxIpAdapter], "diffusers"),
     (None, "51aed3d27d482fceb5e0739b03060e8f", ["sd3_dit", "sd3_vae_encoder", "sd3_vae_decoder"], [SD3DiT, SD3VAEEncoder, SD3VAEDecoder], "civitai"),
     (None, "98cc34ccc5b54ae0e56bdea8688dcd5a", ["sd3_text_encoder_2"], [SD3TextEncoder2], "civitai"),
@@ -103,6 +115,16 @@ model_loader_configs = [
     (None, "aeb82dce778a03dcb4d726cb03f3c43f", ["hunyuan_video_vae_decoder", "hunyuan_video_vae_encoder"], [HunyuanVideoVAEDecoder, HunyuanVideoVAEEncoder], "diffusers"),
     (None, "b9588f02e78f5ccafc9d7c0294e46308", ["hunyuan_video_dit"], [HunyuanVideoDiT], "civitai"),
     (None, "84ef4bd4757f60e906b54aa6a7815dc6", ["hunyuan_video_dit"], [HunyuanVideoDiT], "civitai"),
+    (None, "68beaf8429b7c11aa8ca05b1bd0058bd", ["stepvideo_vae"], [StepVideoVAE], "civitai"),
+    (None, "5c0216a2132b082c10cb7a0e0377e681", ["stepvideo_dit"], [StepVideoModel], "civitai"),
+    (None, "9269f8db9040a9d860eaca435be61814", ["wan_video_dit"], [WanModel], "civitai"),
+    (None, "aafcfd9672c3a2456dc46e1cb6e52c70", ["wan_video_dit"], [WanModel], "civitai"),
+    (None, "6bfcfb3b342cb286ce886889d519a77e", ["wan_video_dit"], [WanModel], "civitai"),
+    (None, "cb104773c6c2cb6df4f9529ad5c60d0b", ["wan_video_dit"], [WanModel], "diffusers"),
+    (None, "9c8818c2cbea55eca56c7b447df170da", ["wan_video_text_encoder"], [WanTextEncoder], "civitai"),
+    (None, "5941c53e207d62f20f9025686193c40b", ["wan_video_image_encoder"], [WanImageEncoder], "civitai"),
+    (None, "1378ea763357eea97acdef78e65d6d96", ["wan_video_vae"], [WanVideoVAE], "civitai"),
+    (None, "ccc42284ea13e1ad04693284c7a09be6", ["wan_video_vae"], [WanVideoVAE], "civitai"),
 ]
 huggingface_model_loader_configs = [
     # These configs are provided for detecting model type automatically.
@@ -115,7 +137,9 @@ huggingface_model_loader_configs = [
     ("T5EncoderModel", "diffsynth.models.flux_text_encoder", "flux_text_encoder_2", "FluxTextEncoder2"),
     ("CogVideoXTransformer3DModel", "diffsynth.models.cog_dit", "cog_dit", "CogDiT"),
     ("SiglipModel", "transformers.models.siglip.modeling_siglip", "siglip_vision_model", "SiglipVisionModel"),
-    ("LlamaForCausalLM", "diffsynth.models.hunyuan_video_text_encoder", "hunyuan_video_text_encoder_2", "HunyuanVideoLLMEncoder")
+    ("LlamaForCausalLM", "diffsynth.models.hunyuan_video_text_encoder", "hunyuan_video_text_encoder_2", "HunyuanVideoLLMEncoder"),
+    ("LlavaForConditionalGeneration", "diffsynth.models.hunyuan_video_text_encoder", "hunyuan_video_text_encoder_2", "HunyuanVideoMLLMEncoder"),
+    ("Step1Model", "diffsynth.models.stepvideo_text_encoder", "stepvideo_text_encoder_2", "STEP1TextEncoder"),
 ]
 patch_model_loader_configs = [
     # These configs are provided for detecting model type automatically.
@@ -577,6 +601,25 @@ preset_models_on_modelscope = {
             "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/image_encoder",
         ],
     },
+    "InfiniteYou":{
+        "file_list":[
+            ("ByteDance/InfiniteYou", "infu_flux_v1.0/aes_stage2/InfuseNetModel/diffusion_pytorch_model-00001-of-00002.safetensors", "models/InfiniteYou/InfuseNetModel"),
+            ("ByteDance/InfiniteYou", "infu_flux_v1.0/aes_stage2/InfuseNetModel/diffusion_pytorch_model-00002-of-00002.safetensors", "models/InfiniteYou/InfuseNetModel"),
+            ("ByteDance/InfiniteYou", "infu_flux_v1.0/aes_stage2/image_proj_model.bin", "models/InfiniteYou"),
+            ("ByteDance/InfiniteYou", "supports/insightface/models/antelopev2/1k3d68.onnx", "models/InfiniteYou/insightface/models/antelopev2"),
+            ("ByteDance/InfiniteYou", "supports/insightface/models/antelopev2/2d106det.onnx", "models/InfiniteYou/insightface/models/antelopev2"),
+            ("ByteDance/InfiniteYou", "supports/insightface/models/antelopev2/genderage.onnx", "models/InfiniteYou/insightface/models/antelopev2"),
+            ("ByteDance/InfiniteYou", "supports/insightface/models/antelopev2/glintr100.onnx", "models/InfiniteYou/insightface/models/antelopev2"),
+            ("ByteDance/InfiniteYou", "supports/insightface/models/antelopev2/scrfd_10g_bnkps.onnx", "models/InfiniteYou/insightface/models/antelopev2"),            
+        ],
+        "load_path":[
+            [
+                "models/InfiniteYou/InfuseNetModel/diffusion_pytorch_model-00001-of-00002.safetensors",
+                "models/InfiniteYou/InfuseNetModel/diffusion_pytorch_model-00002-of-00002.safetensors"
+            ],
+            "models/InfiniteYou/image_proj_model.bin",
+            ],
+    },
     # ESRGAN
     "ESRGAN_x4": [
         ("AI-ModelScope/Real-ESRGAN", "RealESRGAN_x4.pth", "models/ESRGAN"),
@@ -657,6 +700,25 @@ preset_models_on_modelscope = {
             "models/HunyuanVideo/transformers/mp_rank_00_model_states.pt"
         ],
     },
+    "HunyuanVideoI2V":{
+        "file_list": [
+            ("AI-ModelScope/clip-vit-large-patch14", "model.safetensors", "models/HunyuanVideoI2V/text_encoder"),
+            ("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model-00001-of-00004.safetensors", "models/HunyuanVideoI2V/text_encoder_2"),
+            ("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model-00002-of-00004.safetensors", "models/HunyuanVideoI2V/text_encoder_2"),
+            ("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model-00003-of-00004.safetensors", "models/HunyuanVideoI2V/text_encoder_2"),
+            ("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model-00004-of-00004.safetensors", "models/HunyuanVideoI2V/text_encoder_2"),
+            ("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "config.json", "models/HunyuanVideoI2V/text_encoder_2"),
+            ("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model.safetensors.index.json", "models/HunyuanVideoI2V/text_encoder_2"),
+            ("AI-ModelScope/HunyuanVideo-I2V", "hunyuan-video-i2v-720p/vae/pytorch_model.pt", "models/HunyuanVideoI2V/vae"),
+            ("AI-ModelScope/HunyuanVideo-I2V", "hunyuan-video-i2v-720p/transformers/mp_rank_00_model_states.pt", "models/HunyuanVideoI2V/transformers")
+        ],
+        "load_path": [
+            "models/HunyuanVideoI2V/text_encoder/model.safetensors",
+            "models/HunyuanVideoI2V/text_encoder_2",
+            "models/HunyuanVideoI2V/vae/pytorch_model.pt",
+            "models/HunyuanVideoI2V/transformers/mp_rank_00_model_states.pt"
+        ],
+    },
     "HunyuanVideo-fp8":{
         "file_list": [
             ("AI-ModelScope/clip-vit-large-patch14", "model.safetensors", "models/HunyuanVideo/text_encoder"),
@@ -717,6 +779,7 @@ Preset_model_id: TypeAlias = Literal[
     "Shakker-Labs/FLUX.1-dev-ControlNet-Depth",
     "Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro",
     "InstantX/FLUX.1-dev-IP-Adapter",
+    "InfiniteYou",
     "SDXL_lora_zyd232_ChineseInkStyle_SDXL_v1_0",
     "QwenPrompt",
     "OmostPrompt",
@@ -733,4 +796,5 @@ Preset_model_id: TypeAlias = Literal[
     "StableDiffusion3.5-medium",
     "HunyuanVideo",
     "HunyuanVideo-fp8",
+    "HunyuanVideoI2V",
 ]

{diffsynth-1.1.1 → diffsynth-1.1.3}/diffsynth/controlnets/processors.py

@@ -1,10 +1,4 @@
 from typing_extensions import Literal, TypeAlias
-import warnings
-with warnings.catch_warnings():
-    warnings.simplefilter("ignore")
-    from controlnet_aux.processor import (
-        CannyDetector, MidasDetector, HEDdetector, LineartDetector, LineartAnimeDetector, OpenposeDetector, NormalBaeDetector
-    )
 
 
 Processor_id: TypeAlias = Literal[
@@ -15,18 +9,25 @@ class Annotator:
     def __init__(self, processor_id: Processor_id, model_path="models/Annotators", detect_resolution=None, device='cuda', skip_processor=False):
         if not skip_processor:
             if processor_id == "canny":
+                from controlnet_aux.processor import CannyDetector
                 self.processor = CannyDetector()
             elif processor_id == "depth":
+                from controlnet_aux.processor import MidasDetector
                 self.processor = MidasDetector.from_pretrained(model_path).to(device)
             elif processor_id == "softedge":
+                from controlnet_aux.processor import HEDdetector
                 self.processor = HEDdetector.from_pretrained(model_path).to(device)
             elif processor_id == "lineart":
+                from controlnet_aux.processor import LineartDetector
                 self.processor = LineartDetector.from_pretrained(model_path).to(device)
             elif processor_id == "lineart_anime":
+                from controlnet_aux.processor import LineartAnimeDetector
                 self.processor = LineartAnimeDetector.from_pretrained(model_path).to(device)
             elif processor_id == "openpose":
+                from controlnet_aux.processor import OpenposeDetector
                 self.processor = OpenposeDetector.from_pretrained(model_path).to(device)
             elif processor_id == "normal":
+                from controlnet_aux.processor import NormalBaeDetector
                 self.processor = NormalBaeDetector.from_pretrained(model_path).to(device)
             elif processor_id == "tile" or processor_id == "none" or processor_id == "inpaint":
                 self.processor = None

{diffsynth-1.1.1 → diffsynth-1.1.3}/diffsynth/data/video.py

@@ -135,8 +135,8 @@ class VideoData:
             frame.save(os.path.join(folder, f"{i}.png"))
 
 
-def save_video(frames, save_path, fps, quality=9):
-    writer = imageio.get_writer(save_path, fps=fps, quality=quality)
+def save_video(frames, save_path, fps, quality=9, ffmpeg_params=None):
+    writer = imageio.get_writer(save_path, fps=fps, quality=quality, ffmpeg_params=ffmpeg_params)
     for frame in tqdm(frames, desc="Saving video"):
         frame = np.array(frame)
         writer.append_data(frame)

diffsynth-1.1.3/diffsynth/distributed/xdit_context_parallel.py

@@ -0,0 +1,129 @@
+import torch
+from typing import Optional
+from einops import rearrange
+from xfuser.core.distributed import (get_sequence_parallel_rank,
+                                     get_sequence_parallel_world_size,
+                                     get_sp_group)
+from xfuser.core.long_ctx_attention import xFuserLongContextAttention
+
+def sinusoidal_embedding_1d(dim, position):
+    sinusoid = torch.outer(position.type(torch.float64), torch.pow(
+        10000, -torch.arange(dim//2, dtype=torch.float64, device=position.device).div(dim//2)))
+    x = torch.cat([torch.cos(sinusoid), torch.sin(sinusoid)], dim=1)
+    return x.to(position.dtype)
+
+def pad_freqs(original_tensor, target_len):
+    seq_len, s1, s2 = original_tensor.shape
+    pad_size = target_len - seq_len
+    padding_tensor = torch.ones(
+        pad_size,
+        s1,
+        s2,
+        dtype=original_tensor.dtype,
+        device=original_tensor.device)
+    padded_tensor = torch.cat([original_tensor, padding_tensor], dim=0)
+    return padded_tensor
+    
+def rope_apply(x, freqs, num_heads):
+    x = rearrange(x, "b s (n d) -> b s n d", n=num_heads)
+    s_per_rank = x.shape[1]
+
+    x_out = torch.view_as_complex(x.to(torch.float64).reshape(
+        x.shape[0], x.shape[1], x.shape[2], -1, 2))
+
+    sp_size = get_sequence_parallel_world_size()
+    sp_rank = get_sequence_parallel_rank()
+    freqs = pad_freqs(freqs, s_per_rank * sp_size)
+    freqs_rank = freqs[(sp_rank * s_per_rank):((sp_rank + 1) * s_per_rank), :, :]
+
+    x_out = torch.view_as_real(x_out * freqs_rank).flatten(2)
+    return x_out.to(x.dtype)
+
+def usp_dit_forward(self,
+            x: torch.Tensor,
+            timestep: torch.Tensor,
+            context: torch.Tensor,
+            clip_feature: Optional[torch.Tensor] = None,
+            y: Optional[torch.Tensor] = None,
+            use_gradient_checkpointing: bool = False,
+            use_gradient_checkpointing_offload: bool = False,
+            **kwargs,
+            ):
+    t = self.time_embedding(
+        sinusoidal_embedding_1d(self.freq_dim, timestep))
+    t_mod = self.time_projection(t).unflatten(1, (6, self.dim))
+    context = self.text_embedding(context)
+    
+    if self.has_image_input:
+        x = torch.cat([x, y], dim=1)  # (b, c_x + c_y, f, h, w)
+        clip_embdding = self.img_emb(clip_feature)
+        context = torch.cat([clip_embdding, context], dim=1)
+    
+    x, (f, h, w) = self.patchify(x)
+    
+    freqs = torch.cat([
+        self.freqs[0][:f].view(f, 1, 1, -1).expand(f, h, w, -1),
+        self.freqs[1][:h].view(1, h, 1, -1).expand(f, h, w, -1),
+        self.freqs[2][:w].view(1, 1, w, -1).expand(f, h, w, -1)
+    ], dim=-1).reshape(f * h * w, 1, -1).to(x.device)
+    
+    def create_custom_forward(module):
+        def custom_forward(*inputs):
+            return module(*inputs)
+        return custom_forward
+
+    # Context Parallel
+    x = torch.chunk(
+        x, get_sequence_parallel_world_size(),
+        dim=1)[get_sequence_parallel_rank()]
+
+    for block in self.blocks:
+        if self.training and use_gradient_checkpointing:
+            if use_gradient_checkpointing_offload:
+                with torch.autograd.graph.save_on_cpu():
+                    x = torch.utils.checkpoint.checkpoint(
+                        create_custom_forward(block),
+                        x, context, t_mod, freqs,
+                        use_reentrant=False,
+                    )
+            else:
+                x = torch.utils.checkpoint.checkpoint(
+                    create_custom_forward(block),
+                    x, context, t_mod, freqs,
+                    use_reentrant=False,
+                )
+        else:
+            x = block(x, context, t_mod, freqs)
+
+    x = self.head(x, t)
+
+    # Context Parallel
+    x = get_sp_group().all_gather(x, dim=1)
+
+    # unpatchify
+    x = self.unpatchify(x, (f, h, w))
+    return x
+
+
+def usp_attn_forward(self, x, freqs):
+    q = self.norm_q(self.q(x))
+    k = self.norm_k(self.k(x))
+    v = self.v(x)
+
+    q = rope_apply(q, freqs, self.num_heads)
+    k = rope_apply(k, freqs, self.num_heads)
+    q = rearrange(q, "b s (n d) -> b s n d", n=self.num_heads)
+    k = rearrange(k, "b s (n d) -> b s n d", n=self.num_heads)
+    v = rearrange(v, "b s (n d) -> b s n d", n=self.num_heads)
+
+    x = xFuserLongContextAttention()(
+        None,
+        query=q,
+        key=k,
+        value=v,
+    )
+    x = x.flatten(2)
+
+    del q, k, v
+    torch.cuda.empty_cache()
+    return self.o(x)

diffsynth-1.1.3/diffsynth/extensions/ImageQualityMetric/BLIP/__init__.py

@@ -0,0 +1 @@
+from .blip_pretrain import *

diffsynth-1.1.3/diffsynth/extensions/ImageQualityMetric/BLIP/blip.py

@@ -0,0 +1,77 @@
+'''
+ * Adapted from BLIP (https://github.com/salesforce/BLIP)
+'''
+
+import warnings
+warnings.filterwarnings("ignore")
+
+import torch
+import os
+from urllib.parse import urlparse
+from timm.models.hub import download_cached_file
+from transformers import BertTokenizer
+from .vit import VisionTransformer, interpolate_pos_embed
+
+
+def default_bert():
+    current_dir = os.path.dirname(os.path.abspath(__file__))
+    project_root = os.path.abspath(os.path.join(current_dir, '../../../../'))
+    model_path = os.path.join(project_root, 'models', 'QualityMetric')
+    return os.path.join(model_path, "bert-base-uncased")
+
+
+def init_tokenizer(bert_model_path):
+    tokenizer = BertTokenizer.from_pretrained(bert_model_path)
+    tokenizer.add_special_tokens({'bos_token':'[DEC]'})
+    tokenizer.add_special_tokens({'additional_special_tokens':['[ENC]']})       
+    tokenizer.enc_token_id = tokenizer.additional_special_tokens_ids[0]  
+    return tokenizer
+
+
+def create_vit(vit, image_size, use_grad_checkpointing=False, ckpt_layer=0, drop_path_rate=0):
+        
+    assert vit in ['base', 'large'], "vit parameter must be base or large"
+    if vit=='base':
+        vision_width = 768
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=12, 
+                                           num_heads=12, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0 or drop_path_rate
+                                          )   
+    elif vit=='large':
+        vision_width = 1024
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=24, 
+                                           num_heads=16, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0.1 or drop_path_rate
+                                          )   
+    return visual_encoder, vision_width
+
+
+def is_url(url_or_filename):
+    parsed = urlparse(url_or_filename)
+    return parsed.scheme in ("http", "https")
+
+def load_checkpoint(model,url_or_filename):
+    if is_url(url_or_filename):
+        cached_file = download_cached_file(url_or_filename, check_hash=False, progress=True)
+        checkpoint = torch.load(cached_file, map_location='cpu') 
+    elif os.path.isfile(url_or_filename):        
+        checkpoint = torch.load(url_or_filename, map_location='cpu') 
+    else:
+        raise RuntimeError('checkpoint url or path is invalid')
+        
+    state_dict = checkpoint['model']
+    
+    state_dict['visual_encoder.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder.pos_embed'],model.visual_encoder) 
+    if 'visual_encoder_m.pos_embed' in model.state_dict().keys():
+        state_dict['visual_encoder_m.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder_m.pos_embed'],
+                                                                         model.visual_encoder_m)    
+    for key in model.state_dict().keys():
+        if key in state_dict.keys():
+            if state_dict[key].shape!=model.state_dict()[key].shape:
+                print(key, ": ", state_dict[key].shape, ', ', model.state_dict()[key].shape)
+                del state_dict[key]
+    
+    msg = model.load_state_dict(state_dict,strict=False)
+    print('load checkpoint from %s'%url_or_filename)  
+    return model,msg
+    

diffsynth-1.1.3/diffsynth/extensions/ImageQualityMetric/BLIP/blip_pretrain.py

@@ -0,0 +1,44 @@
+'''
+ * Adapted from BLIP (https://github.com/salesforce/BLIP)
+'''
+
+import transformers
+transformers.logging.set_verbosity_error()
+
+from torch import nn
+import os
+from .med import BertConfig, BertModel
+from .blip import create_vit, init_tokenizer
+
+class BLIP_Pretrain(nn.Module):
+    def __init__(self,                 
+                 med_config = "med_config.json",  
+                 image_size = 224,
+                 vit = 'base',
+                 vit_grad_ckpt = False,
+                 vit_ckpt_layer = 0,                    
+                 embed_dim = 256,     
+                 queue_size = 57600,
+                 momentum = 0.995,
+                 bert_model_path = ""
+                 ):
+        """
+        Args:
+            med_config (str): path for the mixture of encoder-decoder model's configuration file
+            image_size (int): input image size
+            vit (str): model size of vision transformer
+        """               
+        super().__init__()
+        
+        self.visual_encoder, vision_width = create_vit(vit,image_size, vit_grad_ckpt, vit_ckpt_layer, 0)
+        
+        self.tokenizer = init_tokenizer(bert_model_path)   
+        encoder_config = BertConfig.from_json_file(med_config)
+        encoder_config.encoder_width = vision_width
+        self.text_encoder = BertModel(config=encoder_config, add_pooling_layer=False)
+
+        text_width = self.text_encoder.config.hidden_size
+        
+        self.vision_proj = nn.Linear(vision_width, embed_dim)
+        self.text_proj = nn.Linear(text_width, embed_dim)
+