diff --git a/README.md b/README.md index 7093950..ceac65d 100644 --- a/README.md +++ b/README.md @@ -212,6 +212,7 @@ save_video(video, "video1.mp4", fps=15, quality=5) |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-I2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-I2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-I2V-A14B.py)| |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](./examples/wanvideo/model_inference/Wan2.2-T2V-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-T2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-T2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-T2V-A14B.py)| |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-TI2V-5B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-TI2V-5B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-TI2V-5B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-TI2V-5B.py)| +|[Wan-AI/Wan2.2-VACE-Fun-A14B](https://www.modelscope.cn/models/PAI/Wan2.2-VACE-Fun-A14B)|`vace_control_video`, `vace_reference_image`|[code](./examples/wanvideo/model_inference/Wan2.2-VACE-Fun-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-VACE-Fun-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-VACE-Fun-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-VACE-Fun-A14B.py)| |[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-InP.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)| |[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)| |[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)| diff --git a/README_zh.md b/README_zh.md index a9bd0ca..2639c6f 100644 --- a/README_zh.md +++ b/README_zh.md @@ -212,6 +212,7 @@ save_video(video, "video1.mp4", fps=15, quality=5) |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-I2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-I2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-I2V-A14B.py)| |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](./examples/wanvideo/model_inference/Wan2.2-T2V-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-T2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-T2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-T2V-A14B.py)| |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-TI2V-5B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-TI2V-5B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-TI2V-5B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-TI2V-5B.py)| +|[Wan-AI/Wan2.2-VACE-Fun-A14B](https://www.modelscope.cn/models/PAI/Wan2.2-VACE-Fun-A14B)|`vace_control_video`, `vace_reference_image`|[code](./examples/wanvideo/model_inference/Wan2.2-VACE-Fun-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-VACE-Fun-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-VACE-Fun-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-VACE-Fun-A14B.py)| |[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-InP.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)| |[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)| |[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)| diff --git a/diffsynth/pipelines/wan_video_new.py b/diffsynth/pipelines/wan_video_new.py index 4895247..6adf851 100644 --- a/diffsynth/pipelines/wan_video_new.py +++ b/diffsynth/pipelines/wan_video_new.py @@ -543,7 +543,11 @@ class WanVideoPipeline(BasePipeline): # VACE (TODO: remove it) if vace_reference_image is not None or (animate_pose_video is not None and animate_face_video is not None): - inputs_shared["latents"] = inputs_shared["latents"][:, :, 1:] + if vace_reference_image is not None and isinstance(vace_reference_image, list): + f = len(vace_reference_image) + else: + f = 1 + inputs_shared["latents"] = inputs_shared["latents"][:, :, f:] # post-denoising, pre-decoding processing logic for unit in self.post_units: inputs_shared, _, _ = self.unit_runner(unit, self, inputs_shared, inputs_posi, inputs_nega) @@ -598,7 +602,9 @@ class WanVideoUnit_InputVideoEmbedder(PipelineUnit): input_video = pipe.preprocess_video(input_video) input_latents = pipe.vae.encode(input_video, device=pipe.device, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride).to(dtype=pipe.torch_dtype, device=pipe.device) if vace_reference_image is not None: - vace_reference_image = pipe.preprocess_video([vace_reference_image]) + if not isinstance(vace_reference_image, list): + vace_reference_image = [vace_reference_image] + vace_reference_image = pipe.preprocess_video(vace_reference_image) vace_reference_latents = pipe.vae.encode(vace_reference_image, device=pipe.device).to(dtype=pipe.torch_dtype, device=pipe.device) input_latents = torch.concat([vace_reference_latents, input_latents], dim=2) if pipe.scheduler.training: @@ -900,11 +906,12 @@ class WanVideoUnit_VACE(PipelineUnit): for j in range(f): new_vace_ref_images.append(vace_reference_image[0, :, j:j+1]) vace_reference_image = new_vace_ref_images - - vace_reference_image = pipe.preprocess_video([vace_reference_image]) + vace_reference_latents = pipe.vae.encode(vace_reference_image, device=pipe.device, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride).to(dtype=pipe.torch_dtype, device=pipe.device) - vace_reference_latents = torch.concat((*vace_reference_latents, torch.zeros_like(vace_reference_latents)), dim=1) - vace_video_latents = torch.concat((vace_reference_latents, vace_video_latents), dim=2) + vace_reference_latents = torch.concat((vace_reference_latents, torch.zeros_like(vace_reference_latents)), dim=1) + vace_reference_latents = [u.unsqueeze(0) for u in vace_reference_latents] + + vace_video_latents = torch.concat((*vace_reference_latents, vace_video_latents), dim=2) vace_mask_latents = torch.concat((torch.zeros_like(vace_mask_latents[:, :, :f]), vace_mask_latents), dim=2) vace_context = torch.concat((vace_video_latents, vace_mask_latents), dim=1) diff --git a/examples/wanvideo/README.md b/examples/wanvideo/README.md index 924becd..a45c287 100644 --- a/examples/wanvideo/README.md +++ b/examples/wanvideo/README.md @@ -53,6 +53,7 @@ save_video(video, "video1.mp4", fps=15, quality=5) |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](./model_inference/Wan2.2-I2V-A14B.py)|[code](./model_training/full/Wan2.2-I2V-A14B.sh)|[code](./model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](./model_training/lora/Wan2.2-I2V-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-I2V-A14B.py)| |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](./model_inference/Wan2.2-T2V-A14B.py)|[code](./model_training/full/Wan2.2-T2V-A14B.sh)|[code](./model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](./model_training/lora/Wan2.2-T2V-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-T2V-A14B.py)| |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](./model_inference/Wan2.2-TI2V-5B.py)|[code](./model_training/full/Wan2.2-TI2V-5B.sh)|[code](./model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](./model_training/lora/Wan2.2-TI2V-5B.sh)|[code](./model_training/validate_lora/Wan2.2-TI2V-5B.py)| +|[Wan-AI/Wan2.2-VACE-Fun-A14B](https://www.modelscope.cn/models/PAI/Wan2.2-VACE-Fun-A14B)|`vace_control_video`, `vace_reference_image`|[code](./model_inference/Wan2.2-VACE-Fun-A14B.py)|[code](./model_training/full/Wan2.2-VACE-Fun-A14B.sh)|[code](./model_training/validate_full/Wan2.2-VACE-Fun-A14B.py)|[code](./model_training/lora/Wan2.2-VACE-Fun-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-VACE-Fun-A14B.py)| |[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](./model_inference/Wan2.2-Fun-A14B-InP.py)|[code](./model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)| |[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](./model_inference/Wan2.2-Fun-A14B-Control.py)|[code](./model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)| |[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](./model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)| diff --git a/examples/wanvideo/README_zh.md b/examples/wanvideo/README_zh.md index fa238c8..f3d8eae 100644 --- a/examples/wanvideo/README_zh.md +++ b/examples/wanvideo/README_zh.md @@ -53,6 +53,7 @@ save_video(video, "video1.mp4", fps=15, quality=5) |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](./model_inference/Wan2.2-I2V-A14B.py)|[code](./model_training/full/Wan2.2-I2V-A14B.sh)|[code](./model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](./model_training/lora/Wan2.2-I2V-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-I2V-A14B.py)| |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](./model_inference/Wan2.2-T2V-A14B.py)|[code](./model_training/full/Wan2.2-T2V-A14B.sh)|[code](./model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](./model_training/lora/Wan2.2-T2V-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-T2V-A14B.py)| |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](./model_inference/Wan2.2-TI2V-5B.py)|[code](./model_training/full/Wan2.2-TI2V-5B.sh)|[code](./model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](./model_training/lora/Wan2.2-TI2V-5B.sh)|[code](./model_training/validate_lora/Wan2.2-TI2V-5B.py)| +|[Wan-AI/Wan2.2-VACE-Fun-A14B](https://www.modelscope.cn/models/PAI/Wan2.2-VACE-Fun-A14B)|`vace_control_video`, `vace_reference_image`|[code](./model_inference/Wan2.2-VACE-Fun-A14B.py)|[code](./model_training/full/Wan2.2-VACE-Fun-A14B.sh)|[code](./model_training/validate_full/Wan2.2-VACE-Fun-A14B.py)|[code](./model_training/lora/Wan2.2-VACE-Fun-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-VACE-Fun-A14B.py)| |[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](./model_inference/Wan2.2-Fun-A14B-InP.py)|[code](./model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)| |[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](./model_inference/Wan2.2-Fun-A14B-Control.py)|[code](./model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)| |[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](./model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)| diff --git a/examples/wanvideo/model_training/validate_lora/Wan2.2-VACE-Fun-A14B-lora.py b/examples/wanvideo/model_training/validate_lora/Wan2.2-VACE-Fun-A14B.py similarity index 100% rename from examples/wanvideo/model_training/validate_lora/Wan2.2-VACE-Fun-A14B-lora.py rename to examples/wanvideo/model_training/validate_lora/Wan2.2-VACE-Fun-A14B.py