WAN 2.2 LONGER VIDEOS WORKFLOW!
Added 2025-08-17 16:36:28 +0000 UTCHey everyone! I've just released a quick new video update on GENERATING LONGER VIDEOS WITH WAN 2.2 !
Image to video, text to video AND EVEN video extend!😎 Now you can generate minutes long videos inside the same easy to use and modify workflow!
You can check out the video right here: https://youtu.be/ImJ32AlnM3A
I also created a 1-click installer for the Webui for my Patreon supporters for Local AND Runpod, that you can find right here: https://www.patreon.com/posts/135728905
Here the link to the manual install guide: https://pastebin.com/iuNPnrGm
Down below you will also find the WAN2_2-LONGER_VIDEOS_WORKFLOW.json for free for you to use!
As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some fun😉!
Comments
How do you copy the nodes for further segments? I can eliminate the extras I don't need easily enough but when trying to copy and paste additional segments, as shown in the video, my nodes are scattered all over the place and need to be manually moved AND the lora nodes disappear completely.
Innisfr33
2025-11-13 21:33:19 +0000 UTCHave you a fix for this problem? I want an I2V. i let turn the model 180 degrees around in the first sequence. in the 2end sequence she should turn back but her face is completly diffrent.
Pyriel Löfas
2025-11-05 18:16:48 +0000 UTCCan someone help me? I'm kinda new at this. I totally got this entire thing working after a while, and the biggest problem I have is having to manually enter the dimensions of the initial video in the video2video workflow. If I have like 6 or something flows in there, it gets tiresome, and there is the possibility that I forget one and it messes up the entire video chain. Please, there has to be a way that either it AUTO detects the initial video size and changes the rest to match, or at the very least, you enter it once and then it auto changes the rest regardless of how many chains you have. This is a really good workflow, but it seems this one little part could be automated, and leaves a lot to mess up if you forget a chain.
Scott Beowulf Kaine
2025-09-17 06:50:34 +0000 UTClooking at how many people have issues and how many people actually get responses. Seems a bit unbalanced.
NewBe2
2025-09-13 02:22:04 +0000 UTCadding last part: ETCH ComfyRegistry Data: 60/96 FETCH ComfyRegistry Data: 65/96 FETCH ComfyRegistry Data: 70/96 FETCH ComfyRegistry Data: 75/96 FETCH ComfyRegistry Data: 80/96 FETCH ComfyRegistry Data: 85/96 FETCH ComfyRegistry Data: 90/96 FETCH ComfyRegistry Data: 95/96 FETCH ComfyRegistry Data [DONE] [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE] [ComfyUI-Manager] All startup tasks have been completed. 100%|████████████████████████████████████████████████████████████████████████████████████| 2/2 [01:24<00:00, 42.38s/it] !!! Exception during processing !!! cannot reshape array of size 26511568 into shape (5120,5440) Traceback (most recent call last): File "C:\ai\ComfyUI_windows_portable\ComfyUI\execution.py", line 496, in execute output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ai\ComfyUI_windows_portable\ComfyUI\execution.py", line 315, in get_output_data return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ai\ComfyUI_windows_portable\ComfyUI\execution.py", line 289, in _async_map_node_over_list await process_inputs(input_dict, i) File "C:\ai\ComfyUI_windows_portable\ComfyUI\execution.py", line 277, in process_inputs result = f(**inputs) ^^^^^^^^^^^ File "C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 152, in load_unet sd = gguf_sd_loader(unet_path) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py", line 55, in gguf_sd_loader reader = gguf.GGUFReader(path) ^^^^^^^^^^^^^^^^^^^^^ File "C:\ai\ComfyUI_windows_portable\python_embeded\Lib\site-packages\gguf\gguf_reader.py", line 182, in __init__ self._build_tensors(offs, tensors_fields) File "C:\ai\ComfyUI_windows_portable\python_embeded\Lib\site-packages\gguf\gguf_reader.py", line 364, in _build_tensors data = self._get(data_offs, item_type, item_count).reshape(np_dims), ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ValueError: cannot reshape array of size 26511568 into shape (5120,5440) Prompt executed in 117.21 seconds
NewBe2
2025-09-01 21:29:57 +0000 UTClike some others I am getting the: UnetLoaderGGUF cannot reshape array of size 26511568 into shape (5120,5440) I have a single 5090. I am doing text to image but this happens with text to video as well. I have the same issue in both the wan 2.2 load and the wan 2.2 extended video. I am using your initial setup recreating your image with no changes. I have not gone back to doing a complete reinstall. Below is the terminal box text: C:\ai\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build [START] Security scan [DONE] Security scan ## ComfyUI-Manager: installing dependencies done. ** ComfyUI startup time: 2025-09-01 09:18:18.533 ** Platform: Windows ** Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)] ** Python executable: C:\ai\ComfyUI_windows_portable\python_embeded\python.exe ** ComfyUI Path: C:\ai\ComfyUI_windows_portable\ComfyUI ** ComfyUI Base Folder Path: C:\ai\ComfyUI_windows_portable\ComfyUI ** User directory: C:\ai\ComfyUI_windows_portable\ComfyUI\user ** ComfyUI-Manager config path: C:\ai\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Manager\config.ini ** Log path: C:\ai\ComfyUI_windows_portable\ComfyUI\user\comfyui.log Prestartup times for custom nodes: 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use 2.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager Checkpoint files will always be loaded safely. Total VRAM 32607 MB, total RAM 65295 MB pytorch version: 2.8.0+cu128 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync Using pytorch attention Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)] ComfyUI version: 0.3.56 ComfyUI frontend version: 1.25.11 [Prompt Server] web root: C:\ai\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static [ComfyUI-Easy-Use] server: v1.3.3 Loaded [ComfyUI-Easy-Use] web root: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use\web_version/v2 Loaded ComfyUI-GGUF: Allowing full torch compile Traceback (most recent call last): File "C:\ai\ComfyUI_windows_portable\ComfyUI\nodes.py", line 2129, in load_custom_node module_spec.loader.exec_module(module) File "", line 999, in exec_module File "", line 488, in _call_with_frames_removed File "C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-hunyuanvideowrapper\__init__.py", line 1, in from .nodes import NODE_CLASS_MAPPINGS as NODES_CLASS, NODE_DISPLAY_NAME_MAPPINGS as NODES_DISPLAY File "C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-hunyuanvideowrapper\nodes.py", line 10, in from .hyvideo.text_encoder import TextEncoder File "C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-hunyuanvideowrapper\hyvideo\text_encoder\__init__.py", line 9, in from .processing_llava import LlavaProcessor File "C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-hunyuanvideowrapper\hyvideo\text_encoder\processing_llava.py", line 23, in from transformers.processing_utils import ProcessingKwargs, ProcessorMixin, Unpack, _validate_images_text_input_order ImportError: cannot import name '_validate_images_text_input_order' from 'transformers.processing_utils' (C:\ai\ComfyUI_windows_portable\python_embeded\Lib\site-packages\transformers\processing_utils.py) Cannot import C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-hunyuanvideowrapper module for custom nodes: cannot import name '_validate_images_text_input_order' from 'transformers.processing_utils' (C:\ai\ComfyUI_windows_portable\python_embeded\Lib\site-packages\transformers\processing_utils.py) ### Loading: ComfyUI-Manager (V3.36) [ComfyUI-Manager] network_mode: public ### ComfyUI Version: v0.3.56-6-g9b151559 | Released on '2025-08-31' __ ______ ____ ____ ____ _ _ \ \ / / _ \ / ___| __ _ _ __ ___ ___| _ \ _____ __/ ___(_)_ __| | \ \ / /| |_) | | _ / _` | '_ ` _ \ / _ \ | | |/ _ \ \ / / | _| | '__| | \ V / | _ <| |_| | (_| | | | | | | __/ |_| | __/\ V /| |_| | | | | | \_/ |_| \_\\____|\__,_|_| |_| |_|\___|____/ \___| \_/ \____|_|_| |_| 🎮 VRGameDevGirl custom nodes loaded successfully! 🎞️ [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json ------------------------------------------ Comfyroll Studio v1.76 : 175 Nodes Loaded ------------------------------------------ ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki ------------------------------------------ [C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts [C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False [C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider'] C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py:26: UserWarning: DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly warnings.warn("DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly") # 😺dzNodes: LayerStyle -> Cannot import name 'guidedFilter' from 'cv2.ximgproc' A few nodes cannot works properly, while most nodes are not affected. Please REINSTALL package 'opencv-contrib-python'. For detail refer to https://github.com/chflame163/ComfyUI_LayerStyle/issues/5 [tinyterraNodes] Loaded Using pytorch attention (RES4LYF) Init (RES4LYF) Importing beta samplers. (RES4LYF) Importing legacy samplers. [rgthree-comfy] Loaded 48 exciting nodes. 🎉 WAS Node Suite: OpenCV Python FFMPEG support is enabled WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available. WAS Node Suite: Finished. Loaded 220 nodes successfully. "Every artist was first an amateur." - Ralph Waldo Emerson Import times for custom nodes: 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-vrgamedevgirl 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-mxtoolkit 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-MagCache 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\wlsh_nodes 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-custom-scripts 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_ultimatesdupscale 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\Derfuu_ComfyUI_ModdedNodes 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\gguf 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux 0.0 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite 0.1 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_tinyterranodes 0.1 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_LayerStyle 0.1 seconds (IMPORT FAILED): C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-hunyuanvideowrapper 0.1 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy 0.1 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-advancedliveportrait 0.1 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager 0.2 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\RES4LYF 0.2 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-liveportraitkj 0.2 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_essentials 0.4 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes 0.8 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui 1.4 seconds: C:\ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use Context impl SQLiteImpl. Will assume non-transactional DDL. No target revision found. Starting server To see the GUI go to: http://127.0.0.1:8188 FETCH ComfyRegistry Data: 5/96 FETCH ComfyRegistry Data: 10/96 got prompt Using pytorch attention in VAE Using pytorch attention in VAE VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16 FETCH ComfyRegistry Data: 15/96 FETCH ComfyRegistry Data: 20/96 gguf qtypes: Q5_K (168), F32 (73), Q6_K (1) Attempting to recreate sentencepiece tokenizer from GGUF file metadata... FETCH ComfyRegistry Data: 25/96 FETCH ComfyRegistry Data: 30/96 Created tokenizer with vocab size of 256384 Dequantizing token_embd.weight to prevent runtime OOM. CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16 gguf qtypes: F16 (694), Q8_0 (400), F32 (1) model weight dtype torch.float16, manual cast: None model_type FLOW Requested to load WanTEModel FETCH ComfyRegistry Data: 35/96 loaded completely 29323.8 5039.953125 True Requested to load WAN21 FETCH ComfyRegistry Data: 40/96 FETCH ComfyRegistry Data: 45/96 loaded partially 14529.994980926513 14529.990356445312 0 Attempting to release mmap (174) FETCH ComfyRegistry Data: 50/96 0%| | 0/2 [00:00
NewBe2
2025-09-01 16:21:08 +0000 UTCquestion, can the two samplers be on random or do they have to be the same?
kristopher ulley
2025-08-30 21:17:11 +0000 UTCwhat types of generation times is everyone getting?
Stevo T
2025-08-24 02:39:21 +0000 UTCIs there a node that let's you resize to a different aspect ratio specifically for 9:16 for image to video
Stevo T
2025-08-24 02:14:46 +0000 UTCDear Aiteepreneur, would this be possible with image to image to image to image?
rubz
2025-08-21 23:29:20 +0000 UTCamazing!
uniqornate
2025-08-21 13:43:23 +0000 UTC
