Home Creators Posts Import Register Favorites Logout

Downloads

Content

For new IPAdapter V2 you need to following models in your ComfyUI.

Some highlighted things you need in order to get started.

/ComfyUI/models/clip_vision

CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors, download and rename

CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors, download and rename

/ComfyUI/models/ipadapter, create it if not present

ip-adapter_sd15.safetensors, Basic model, average strength

ip-adapter_sd15_light_v11.bin, Light impact model

ip-adapter-plus_sd15.safetensors, Plus model, very strong

ip-adapter-plus-face_sd15.safetensors, Face model, portraits

ip-adapter-full-face_sd15.safetensors, Stronger face model, not necessarily better

ip-adapter_sd15_vit-G.safetensors, Base model, requires bigG clip vision encoder

ip-adapter_sdxl_vit-h.safetensors, SDXL model

ip-adapter-plus_sdxl_vit-h.safetensors, SDXL plus model

ip-adapter-plus-face_sdxl_vit-h.safetensors, SDXL face model

ip-adapter_sdxl.safetensors, vit-G SDXL model, requires bigG clip vision encoder

Deprecated ip-adapter_sd15_light.safetensors, v1.0 Light impact model

Update , please remember to check out the previous post for Essential Models and Custom Nodes You Need : https://www.patreon.com/posts/rave-animatediff-98757420

IPAdapter Unified Loader

Loads the full stack of models needed for IPAdapter to function. The returned object will contain information regarding the ipadapter and clip vision models.

------------------------------------------------------------------------------------------------

This workflow version named Version 20240331.

We have listed of collection in here : https://www.patreon.com/collection/393434

Comments

Tri Thanh Nguyen

I can not use the workflow because. I can install ReActorFaceSwap and ReActorRestoreFace. How can i fix it?

Jonathan Oh

I can't make clean video like you. Can you share the links of model and controlnet models which you used? With the name in workflow I can't find.

Marco Belletz

Downloaded models, tried updating all but still receive this error message when getting to ksampler: got prompt [rgthree] Using rgthree's optimized recursive execution. [AnimateDiffEvo] - INFO - Sliding context window activated - latents passed in (50) greater than context_length 16. [AnimateDiffEvo] - INFO - Using motion module v3_sd15_mm.ckpt:v3. 0%| | 0/7 [00:01

GT

Hey Benji, I'm at a loss for the moment. I updated everything and now I'm getting an error on the ksampler on all my aniamteDiff workflows. It's "Error occurred when executing KSampler (Efficient): ModelPatcherAndInjector.unpatch_model() got an unexpected keyword argument 'unpatch_weights'" Any idea what this is? IO

GT

,

Lenny Gordon

Hi hi. I've installed the reactor nodes but I am still getting ``` When loading the graph, the following node types were not found: ReActorFaceSwap ReActorRestoreFace ``` Here is the log fail point ``` Traceback (most recent call last): File "J:\CurrentAi\StableComfyC\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1889, in load_custom_node module_spec.loader.exec_module(module) File "", line 940, in exec_module File "", line 241, in _call_with_frames_removed File "J:\CurrentAi\StableComfyC\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Reactor-node\__init__.py", line 23, in from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS File "J:\CurrentAi\StableComfyC\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Reactor-node\nodes.py", line 10, in from insightface.app.common import Face ModuleNotFoundError: No module named 'insightface' ``` Any ideas?

II shishak

Error occurred when executing OneFormer-COCO-SemSegPreprocessor: No module named 'fvcore' File "/content/drive/MyDrive/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/content/drive/MyDrive/ComfyUI/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/content/drive/MyDrive/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/content/drive/MyDrive/ComfyUI/custom_nodes/comfyui_controlnet_aux/node_wrappers/oneformer.py", line 15, in semantic_segmentate from controlnet_aux.oneformer import OneformerSegmentor File "/content/drive/MyDrive/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/oneformer/__init__.py", line 2, in from .api import make_detectron2_model, semantic_run File "/content/drive/MyDrive/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/controlnet_aux/oneformer/api.py", line 6, in from custom_detectron2.config import get_cfg File "/content/drive/MyDrive/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/custom_detectron2/__init__.py", line 5, in setup_environment() File "/content/drive/MyDrive/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/custom_detectron2/utils/env.py", line 108, in setup_environment _configure_libraries() File "/content/drive/MyDrive/ComfyUI/custom_nodes/comfyui_controlnet_aux/src/custom_detectron2/utils/env.py", line 87, in _configure_libraries import fvcore

Eugene Feder

hi).. please tell me where to get animate.motion.checkpoint

Tung Hoang

Error occurred when executing ACN_AdvancedControlNetApply: 'NoneType' object has no attribute 'copy' File "C:\Riot Games\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Riot Games\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Riot Games\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Riot Games\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\nodes.py", line 174, in apply_controlnet c_net = convert_to_advanced(control_net.copy()).set_cond_hint(control_hint, strength, (start_percent, end_percent)) ^^^^^^^^^^^^^^^^ Stuck in this error and has no clue, i'm just a google guy, please help @Benji

Alex Sergeev

Hey, thanks for your job mate! Keep going Seems like workflow misses GetNode and SetNode , but can not get them from UI. Can you please suggest what to do?

Shoghi Castel de Oro

Ahoy! When I try to load this up i just get an error saying 'integer' isn't there.. halp?

Tarun Rishi

Hi Benji, finding that KSampler in AnimateDiff group is very slow (600s/it) on Windows 11 RTX3080 - what setup are you using and are there any optimisations?

Neon Square

I need help, please! I keep getting this error: Error occurred when executing LoadImage: [Errno 2] No such file or directory: 'C:\\Users\\user\\ComfyUI_windows_portable\\ComfyUI\\input\\nancy-profile-pic.png'

Samuel Ericksen

Can you help to solve this error? Error occurred when executing APersonMaskGenerator: 'FieldDescriptor' object has no attribute '_default_constructor'

DoctorSpongefoot

I couldn't find the Integer node and so I replaced it with the DF_Integer and it seems happy now. Would be interested to know is there a specific Integer node you prefer or recommend?

Blaze Origin

Amazing workflow! I have the "integer" Node but I don't have "Integer Width, Integer Height and NumofFrames - Integer" can you let me know where to get this please?

Blaze Origin

Thanks a lot! I have installed and It is still red, was there any other nodes relating to this?

Blaze Origin

Requested to load CLIPVisionModelProjection Loading 1 new model [AnimateDiffEvo] - INFO - Loading motion module v3_sd15_mm.ckpt via Gen2 Requested to load AutoencoderKL Loading 1 new model [AnimateDiffEvo] - INFO - Sliding context window activated - latents passed in (50) greater than context_length 16. [AnimateDiffEvo] - INFO - Using motion module v3_sd15_mm.ckpt:v3. Requested to load ControlNet Requested to load ControlNet Requested to load BaseModel Requested to load AnimateDiffModel Loading 4 new models !!! Exception during processing !!! Traceback (most recent call last): File "C:\Users\adria\Desktop\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all)

Blaze Origin

I'm very close, at the end of the process, this error message would come up. I will experiment to see if I can fix it

Blaze Origin

I fixed it, I renamed controlnet_checkpoint.ckpt into Animate_controlnet_checkpoint.ckpt

John C

I tried downloading RAVE_AnimateDiff_V2V LCM 2IPA Version 20240331.zip but it keeps having an error saving, is this workflow still available?