What's new? : New interface, New upscaler, New model optimisation, New LoRA loader.
Runtime profile
Requirements
VAE · 320 MB · SAFETENSORS · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
Vision model · 1.18 GB · SAFETENSORS · fp16 · full · Civitai · 1329096
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use the 【WAN2.2】 KONTEXT to VIDEO — v2.0 workflow in ComfyUI to turn a text prompt or a person's photo into an initial image and then a video from that image, with optional image upscaling.
FLUX Kontext generates the initial image, and the workflow then creates a video from that image.
The workflow is presented as a 12-node graph, and the v2.0 summary lists a new interface, new upscaler, new model optimisation, and new LoRA loader.
Inputs are a text prompt or a photo of the subject to animate; outputs are an initial image and a video made from it.
Saved images include generation parameters in their metadata for online publishing and remixing.
Enable “Use Nodes V2 (Vue)” in ComfyUI Settings, refresh the page, and then load the workflow.
Install ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.
Other named node packs are: comfyui_pulid_flux_ll; rgthree-comfy; comfyui-custom-scripts; comfyui-multigpu; comfyui-easy-use; comfyui-frame-interpolation; comfyui-florence2; was-node-suite-comfyui; comfyui-kjnodes; ComfyUI-Upscaler-Tensorrt; comfyui-impact-pack; comfyui-mxtoolkit
Other named model items are: ae.safetensors; MiaoshouAI/Florence-2-base-PromptGen-v2.0; flux1-dev-Q8_0.gguf; pulid_flux_v0.9.0.safetensors; clip_vision_h.safetensors; rife47.pth; t5-v1_1-xxl-encoder-Q8_0.gguf; ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors; wan2.1-i
Use the six LoRA slots with individual on/off toggles and strength controls; additional LoRA modules can also be connected.
Toggle the built-in SeedVR2 upscaler on or off.
Documented setup options are base, GGUF, speed, and AIO. Base setup names wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors, wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, flux1-kontext-dev-fp8-e4m3fn.safetensors, t5xxl_fp8_e4m3fn_scaled.s
With “Use Nodes V2 (Vue)” disabled, the workflow may have display problems.
The description names ComfyUI-UmeAiRT-Toolkit, while other node packs and model items are also listed. License information is not provided, so verify the exact files, node sources, workflow version, and usage rights before installing or publishing.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 8691 downloads · Type Workflows · Base model Wan Video
Checkpoint · 11.8 GB · GGUF · fp16 · Civitai · 1452850
MiaoshouAI/Florence-2-base-PromptGen-v2.0
File unverifiedVision model · Hugging Face · MiaoshouAI/Florence-2-base-PromptGen-v2.0
pulid_flux_v0.9.0.safetensors
Not resolvedCheckpoint · Unknown
Checkpoint · Hugging Face
Text encoder · 4.71 GB · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
Text encoder · 6.27 GB · SAFETENSORS · fp8 · pruned · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Text encoder · 308 MB · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
VAE · 242 MB · SAFETENSORS · fp16 · full · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Checkpoint · 16.9 GB · Civitai · 1295569
Node pack · Registry
comfyui-custom-scripts
FoundNode pack · Registry
comfyui-easy-use
FoundNode pack · Registry
comfyui-florence2
PossibleNode pack · Registry
comfyui-frame-interpolation
FoundNode pack · Registry
comfyui-impact-pack
FoundNode pack · Registry
Node pack · Registry
Node pack · Registry
comfyui-mxtoolkit
FoundNode pack · Registry
ComfyUI-Upscaler-Tensorrt
FoundNode pack · Registry
comfyui-videohelpersuite
FoundNode pack · Registry
rgthree-comfy
FoundNode pack · Registry
was-node-suite-comfyui
PossibleNode pack · Registry