VACE is incredibly flexible, this is yet another feature of it. You can even add control frames in as well (not shown in this workflow, but videos/workflows will be coming for that in the future). Check out the...
Runtime profile
Source description
VACE is incredibly flexible, this is yet another feature of it. You can even add control frames in as well (not shown in this workflow, but videos/workflows will be coming for that in the future). Check out the tutorial here if you need more guidance on how to use it!
Estimated VRAM requirement
Estimate unavailable
Model file sizes are not complete enough to calculate this requirement yet.
Requirements
8 requirementsAI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this workflow to animate keyframes from first- and last-frame images and a text prompt with VACE; its graph includes video combining for the output.
The graph includes first-to-last-frame handling, VACE encoding, sampling, decoding, and video combining.
It includes two packaged files: VaceNativeFirstLast.json with 29 nodes and VaceWrapperFirstLast.json with 43 nodes.
Use first- and last-frame images and a text prompt; the graph includes LoadImage, CLIPTextEncode, and WanVideoTextEmbedBridge nodes for image loading and text conditioning.
Suggestion · not verified
PreviewImage and VHS_VideoCombine are included for image previews and video combining.
This is listed as a workflow based on Wan Video 14B t2v.
The listed version is Vace FL Native + Wrapper, published by theartofficialtrainer.
VaceNativeFirstLast.json lists these model files: native_umt5_xxl_fp8_e4m3fn_scaled.safetensors, native_wan_2.1_vae.safetensors, wan2.1_vace_1.3B_fp16.safetensors, and Wan21_CausVid_14B_T2V_lora_rank32.safetensors.
VaceWrapperFirstLast.json lists these model files: native_umt5_xxl_fp8_e4m3fn_scaled.safetensors, Wan2_1_VAE_fp32.safetensors, Wan2_1-VACE_module_14B_bf16.safetensors, wan2.1_t2v_14B_fp8_e4m3fn.safetensors, and Wan21_CausVid_14B_T2V_lora_rank32.safetensors.
The two files list these node packs: comfyui_essentials, comfyui-kjnodes, comfyui-videohelpersuite, ComfyUI-WanVideoWrapper, comfyui_layerstyle, and comfyui-easy-use.
Control frames can be added, but they are not shown in this workflow.
The description points to a tutorial for additional guidance.
Before use, verify that the model files and node packs for your chosen JSON file are available.
Suggestion · not verified
No model-use license is listed, so check applicable usage terms before use.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
2 excerptsSource context: 736 downloads · Type Workflows · Base model Wan Video 14B t2v
native_umt5_xxl_fp8_e4m3fn_scaled.safetensors
Not resolvedText encoder · Unknown
native_wan_2.1_vae.safetensors
Not resolvedVAE · Unknown
wan2.1_vace_1.3B_fp16.safetensors
Not resolvedCheckpoint · Unknown
Wan21_CausVid_14B_T2V_lora_rank32.safetensors
Not resolvedLoRA · Unknown
Node pack · Registry
Node pack · Registry
Source context: 727 downloads · Type Workflows · Base model Wan Video 14B t2v
Node pack · Registry
Node pack · Registry