Official ComfyUI workflow templates: Video part 1 (index 3c2199b)

This is an index of the official ComfyUI workflow templates in the Video category (Video part 1) of github.com/Comfy-Org/workflow_templates, pinned to revision 3c2199b9362457b12b9c60c6cc303501526ebd62 and read on 2026-10-27. These are the templates ComfyUI shows in its template browser. Each line gives the template title and identifier, the models it uses, whether it runs open-source weights or a paid API service, the minimum ComfyUI version, any custom nodes it needs, the kinds of input files it loads and its tags. The workflow JSON for an identifier is at templates/<identifier>.json in the repository. Counts: 150 templates, 42 open source, 93 API service. Most frequent models: Wan (21), MiniMax H3 (17), Wan2.1 (11), Seedance 2.5 (9), Vidu (8), Wan2.2 (8), LTX-2.3 (6), LTX-2.5 (6), Lightricks (6), PixVerse (6), LTX-2 (5), Seedance 2.0 (5). - MiniMax H3: Image to Video [video_minimax_h3_i2v]; models: MiniMax H3; open source; min ComfyUI 0.30.0; inputs: image; tags: Image to Video, Int8, Video - MiniMax H3: Reference to Video [video_minimax_h3_r2v]; models: MiniMax H3; open source; min ComfyUI 0.30.0; inputs: image; tags: Reference to Video, Int8, Video - MiniMax H3: Text to Video [video_minimax_h3_t2v]; models: MiniMax H3; open source; min ComfyUI 0.30.0; tags: Text to Video, Int8, Video - FastH3 OmniRef: Reference to Video [video_fasth3_ominiref_r2v]; models: MiniMax H3; open source; min ComfyUI 0.43.0; inputs: image; tags: Reference to Video, Video - LTX-2.3: Image to Video [video_ltx2_3_i2v]; models: LTX-2.3, Lightricks; open source; min ComfyUI 0.16.4; inputs: image; tags: Image to Video, Video - Wan 2.2 14B Image to Video [video_wan2_2_14B_i2v]; models: Wan, Wan2.2; open source; min ComfyUI 0.16.4; inputs: image; tags: Image to Video, Video; official tutorial linked - LTX-2.5: Image to Video [video_ltx2_5_i2v]; models: LTX-2.5; open source; min ComfyUI 0.32.0; inputs: image; tags: Image to Video, Int8, Video - LTX-2.5: Text to Video [video_ltx2_5_t2v]; models: LTX-2.5; open source; min ComfyUI 0.32.0; tags: Video, Text to Video, Int8 - LTX-2.5 DFR: Image to Video [video_ltx2_5_dfr_i2v]; models: LTX-2.5; open source; min ComfyUI 0.35.0; custom nodes: ComfyUI-LTXVideo; inputs: image; tags: Image to Video, Int8, Video - FastVideo FastH3: Image to Video [video_fastvideo_fasth3_i2v]; models: MiniMax H3; open source; min ComfyUI 0.36.0; inputs: image; tags: Image to Video, Int8 - FastVideo FastH3: Text to Video [video_fastvideo_fasth3_t2v]; models: MiniMax H3; open source; min ComfyUI 0.36.0; tags: Text to Video, Int8 - Seedance2.5 1080P: Image to Video [api_seedance2_5_i2v_1080p]; models: Seedance 2.5; API service; min ComfyUI 0.33.2; inputs: image; tags: API, Image to Video - Seedance 2.5: Reference to Video [api_seedance2_5_r2v]; models: Seedance 2.5; API service; min ComfyUI 0.33.2; inputs: image; tags: API, Reference to Video - LTX-2.3: Image Audio to Video [video_ltx2_3_ia2v]; models: LTX-2.3; open source; min ComfyUI 0.16.4; inputs: audio, image; tags: Image to Video, Lip Sync, Video - FLUX 3 Max: Image to Video [api_flux3_max_i2v]; models: FLUX 3 Video; API service; min ComfyUI 0.42.2; inputs: image; tags: Image to Video, API - FLUX 3 Max: Text to Video [api_flux3_max_t2v]; models: FLUX 3 Video; API service; min ComfyUI 0.42.2; tags: API, Text to Video - LTX-2.3: Text to Video [video_ltx2_3_t2v]; models: LTX-2.3, Lightricks; open source; min ComfyUI 0.16.4; tags: Text to Video, Video - LTX-2.5: FLF2V [video_ltx2_5_flf2v]; models: LTX-2.5; open source; min ComfyUI 0.32.0; inputs: image; tags: FLF2V, Int8, Video - Seedance2.5: Video Editing [api_seedance2_5_video_editing]; models: Seedance 2.5; API service; min ComfyUI 0.33.2; inputs: video; tags: API, Video Edit - Seedance 2.5: Text to Video [api_seedance2_5_t2v]; models: Seedance 2.5; API service; min ComfyUI 0.31.0; tags: API, Text to Video - Seedance2.5 Draft: Reference to Video [api_seedance2_5_draft_r2v]; models: Seedance 2.5; API service; min ComfyUI 0.37.3; inputs: image; tags: API, Reference to Video - Seedance2.5 Draft: Image to Video [api_seedance2_5_draft_i2v]; models: Seedance 2.5; API service; min ComfyUI 0.37.3; inputs: image; tags: API, Image to Video - Wan Animate 2: Motion Transfer [video_wan_animate2]; models: Wan Animate; open source; min ComfyUI 0.36.0; inputs: image, video; tags: Motion Control, Int8 - Wan Animate 2 Distilled: Motion Transfer [video_wan_animate2_distilled]; models: Wan Animate; open source; min ComfyUI 0.31.0; inputs: image, video; tags: Motion Control, Int8 - Higgsfield Genjutsu: Motion Transfer [api_higgsfield_genjutsu_motion_transfer]; models: Genjutsu 1.0; API service; min ComfyUI 0.39.2; inputs: image, video; tags: Character Replacement, Motion Control, Video, Video Edit - SCAIL-2: Character Replacement [video_wan21_scail2_character_replacement]; models: SCAIL-2; open source; min ComfyUI 0.25.0; inputs: image, video; tags: Character Replacement - SCAIL-2 Int8: Character Replacement [video_wan21_scail2_character_replacement_int8]; models: SCAIL-2; open source; min ComfyUI 0.25.0; inputs: image, video; tags: Character Replacement, Int8 - Seedance 2.0: Reference to Video [api_seedance2_0_r2v]; models: Seedance 2.0; API service; min ComfyUI 0.26.2; inputs: image; tags: API, Image to Video, Video - Vidu Q4 Preview: Reference to Video [api_vidu_q4_preview_r2v]; models: Vidu Q4; API service; min ComfyUI 0.39.2; inputs: image; tags: API, Reference to Video - Vidu Q4 Preview: Image to Video [api_vidu_q4_preview_i2v]; models: Vidu Q4; API service; min ComfyUI 0.39.2; inputs: image; tags: API, Image to Video - Seedance2.0: First-Last-Frame to Video [api_seedance2_0_flf2v]; models: Seedance 2.0; API service; min ComfyUI 0.26.2; inputs: image; tags: API, FLF2V, Video - HeyGen Video 1.0: Image to Video [api_heygen_video_1_i2v]; models: HeyGen; API service; min ComfyUI 0.38.1; inputs: image; tags: API, Image to Video - Wan3.0: Image to Video [api_wan3_0_i2v]; models: Wan3.0; API service; min ComfyUI 0.33.4; inputs: image; tags: API, Image to Video - Wan3.0: Reference to Video [api_wan3_0_r2v]; models: Wan3.0; API service; min ComfyUI 0.33.4; inputs: image; tags: API, Reference to Video - Grok: Video generation [api_grok_video]; models: Grok; API service; min ComfyUI 0.11.1; inputs: image; tags: Video, Image to Video, Text to Video, API - Grok Imagine Video 1.5: Image to Video [api_grok_imagine_video_1_5]; models: Grok; API service; min ComfyUI 0.30.0; inputs: image; tags: API, Image to Video - Grok: Reference to Video [api_grok_reference_to_video]; models: Grok; API service; min ComfyUI 0.18.2; inputs: image; tags: API, Character Reference, Video - Seedance 1.0 Pro: Image to Video [api_bytedance_image_to_video]; models: Seedance1.0 Pro, ByteDance; API service; min ComfyUI 0.3.58; inputs: image; tags: API, Image to Video, Video - MiniMax H3 Max: Reference to Video [api_minimax_h3_max_r2v]; models: MiniMax H3; API service; min ComfyUI 0.34.2; inputs: image; tags: API, Reference to Video - MiniMax H3: Multiframe Reference [video_minimax_h3_multiframe_reference]; models: MiniMax H3; open source; min ComfyUI 0.34.0; inputs: image; tags: Reference to Video, Int8 - MiniMax H3 Max Turbo: Image to Video [api_minimax_h3_max_turbo_i2v]; models: MiniMax H3; API service; min ComfyUI 0.34.4; inputs: image; tags: API, Reference to Video - MiniMax H3 Max: Image to Video [api_minimax_h3_max_i2v]; models: MiniMax H3; API service; min ComfyUI 0.34.3; inputs: image; tags: API, Image to Video - MiniMax H3 Fun ControlNet Union [video_minimax_h3_fun_controlnet_union]; models: MiniMax H3; open source; min ComfyUI 0.35.0; inputs: video; tags: ControlNet, Int8 - MiniMax H3: Reference to Video [api_minimax_h3_r2v]; models: MiniMax H3; API service; min ComfyUI 0.30.0; inputs: image; tags: API, Reference to Video, Image to Video - MiniMax H3 Max: Text to Video [api_minimax_h3_max_t2v]; models: MiniMax H3; API service; min ComfyUI 0.34.2; tags: API, Text to Video - MiniMax H3 Max: FLF2V [api_minimax_h3_max_flf2v]; models: MiniMax H3; API service; min ComfyUI 0.34.2; inputs: image; tags: API, FLF2V - Kling 3.0: Video Generation [api_kling_v3_video]; models: Kling 3.0; API service; min ComfyUI 0.13.0; inputs: image; tags: API, Image to Video, Video - Kling 3.0: First Last Frame to Video [api_kling_v3_flf2v]; models: Kling 3.0; API service; min ComfyUI 0.13.0; inputs: image; tags: API, Video, FLF2V - Kling 3.0: Motion Control [api_kling_motion_control3]; models: Kling 3.0; API service; min ComfyUI 0.7.0; inputs: image, video; tags: API, Motion Control - Pruna P-Video 2: Image to Video [api_pruna_p_video_i2v]; models: P-Video-2; API service; min ComfyUI 0.36.0; inputs: image; tags: API, Image to Video - Wan 2.2 14B Text to Video [video_wan2_2_14B_t2v]; models: Wan2.2, Wan; source unstated; min ComfyUI 0.16.4; tags: Text to Video, Video; official tutorial linked - Wan2.1 VACE Inpainting [video_wan_vace_inpainting]; models: Wan2.1, Wan; open source; min ComfyUI 0.20.0; inputs: image, video; tags: Inpainting, Video; official tutorial linked - Wan 2.2 14B First-Last Frame to Video [video_wan2_2_14B_flf2v]; models: Wan2.2, Wan; source unstated; min ComfyUI 0.3.31; inputs: image; tags: FLF2V, Video; official tutorial linked - Wan 2.2 5B Video Generation [video_wan2_2_5B_ti2v]; models: Wan2.2, Wan; source unstated; min ComfyUI 0.3.46; inputs: image; tags: Text to Video, Video - Wan2.1 VACE Control Video [video_wan_vace_14B_v2v]; models: Wan2.1, Wan; source unstated; min ComfyUI 0.3.31; inputs: image, video; tags: Video to Video, Video; official tutorial linked - Wan 2.1 Image to Video [image_to_video_wan]; models: Wan2.1, Wan; source unstated; min ComfyUI 0.3.31; inputs: image; tags: Text to Video, Video; official tutorial linked - Wan 2.2 14B Fun Control [video_wan2_2_14B_fun_control]; models: Wan2.2, Wan; source unstated; min ComfyUI 0.3.50; inputs: image, video; tags: Video to Video, Video, ControlNet; official tutorial linked - Bernini-R: Video Edit [video_bernini_r_video_editing]; models: Bernini-R; open source; min ComfyUI 0.25.0; inputs: image, video; tags: Video Edit - Gemini Omni 1.1 Flash: Video Edit [api_google_gemini_omni_flash_1_1_edit]; models: Gemini Omni 1.1 Flash; API service; min ComfyUI 0.34.2; inputs: video; tags: API, Video Edit - Gemini Omni 1.1 Flash: Image to Video [api_google_gemini_omni_flash_1_1_i2v]; models: Gemini Omni 1.1 Flash; API service; min ComfyUI 0.34.2; inputs: image; tags: API, Image to Video - Gemini Omni 1.1 Flash: Reference to Video [api_google_gemini_omni_flash_1_1_r2v]; models: Gemini Omni 1.1 Flash; API service; min ComfyUI 0.34.2; inputs: image; tags: API, Reference to Video - Gemini Omni 1.1 Flash: Text to Video [api_google_gemini_omni_flash_1_1_t2v]; models: Gemini Omni 1.1 Flash; API service; min ComfyUI 0.34.2; tags: API, Text to Video - LTX-2.3: FLF2V [video_ltx2_3_flf2v]; models: LTX-2.3; open source; min ComfyUI 0.16.4; inputs: image; tags: FLF2V, Video - LTX-2.3: ID LoRA [video_ltx2_3_id_lora]; models: LTX-2.3; open source; min ComfyUI 0.19.0; inputs: audio, image; tags: Lip Sync, Video, Voice Cloning - LTX 2.3 IC-LoRA Union Control [video_ltx2_3_ic_lora]; models: LTX-2.3; open source; min ComfyUI 0.22.0; inputs: image, video; tags: ControlNet, Video - Kling O3: Video Edit [api_kling_o3_video_edit]; models: Kling O3; API service; min ComfyUI 0.8.0; inputs: image, video; tags: Video Edit, API, Video - Kling 4.0: Image to Video [api_kling4_i2v]; models: Kling 4.0; API service; min ComfyUI 0.42.6; inputs: image; tags: API, Image to Video - Kling 4.0: Text to Video [api_kling4_t2v]; models: Kling 4.0; API service; min ComfyUI 0.42.6; tags: API, Text to Video - Kling 4.0: Video Edit [api_kling4_video_edit]; models: Kling 4.0; API service; min ComfyUI 0.42.6; inputs: video; tags: Video Edit, API - Kling 4.0: Reference to Video [api_kling4_r2v]; models: Kling 4.0; API service; min ComfyUI 0.42.6; inputs: image; tags: API, Reference to Video - Kling O3: Reference to Video [api_kling_o3_i2v]; models: Kling O3; API service; min ComfyUI 0.8.0; inputs: image; tags: API, Character Reference, Image to Video - Grok Imagine Video 1.5 Lite: Image to Video [api_grok_imagine_video_1_5_lite_i2v]; models: Grok Imagine Video; API service; min ComfyUI 0.38.2; inputs: image; tags: Image to Video, API - Grok Imagine Video 1.5 Lite: Text to Video [api_grok_imagine_video_1_5_lite_t2v]; models: Grok Imagine Video; API service; min ComfyUI 0.38.2; tags: Text to Video, API - Seedance 2.5: FLF2V [api_seedance2_5_flf2v]; models: Seedance 2.5; API service; min ComfyUI 0.31.0; inputs: image; tags: API, FLF2V - Seedance2.5 Draft: Text to Video [api_seedance2_5_draft_t2v]; models: Seedance 2.5; API service; min ComfyUI 0.37.3; tags: API - LTX-2: Image to Video [video_ltx2_i2v]; models: LTX-2, Lightricks; open source; min ComfyUI 0.8.0; inputs: image; tags: Image to Video, Video - LTX-2: Audio to Video [video_ltx_2_audio_to_video]; models: LTX-2; open source; min ComfyUI 0.8.0; custom nodes: comfyui-kjnodes; inputs: audio, image; tags: Audio to Video, Video - LTX-2 Image to Video (Distilled) [video_ltx2_i2v_distilled]; models: LTX-2, Lightricks; open source; min ComfyUI 0.8.0; inputs: image; tags: Image to Video, Video - LTX-2 Text to Video [video_ltx2_t2v]; models: LTX-2, Lightricks; open source; min ComfyUI 0.8.0; tags: Text to Video, Video - LTX-2 Canny to Video [video_ltx2_canny_to_video]; models: LTX-2, Lightricks; open source; min ComfyUI 0.8.0; inputs: image, video; tags: ControlNet, Video - Seedance 1.5 Pro: Image to Video [api_bytedance_seedance1_5_image_to_video]; models: Seedance; API service; min ComfyUI 0.3.58; inputs: image; tags: API, Image to Video - Seedance 1.5 Pro: FLF2V [api_bytedance_seedance1_5_flf2v]; models: ByteDance, Seedance; API service; min ComfyUI 0.3.58; inputs: image; tags: FLF2V, Image to Video, API - Flux Video Edit [api_flux_video_edit]; models: FLUX; API service; min ComfyUI 0.36.0; inputs: video; tags: API, Video Edit - Wan3.0: Text to Video [api_wan3_0_t2v]; models: Wan3.0; API service; min ComfyUI 0.33.4; tags: API, Text to Video - Wan2.1 SCAIL [video-wan21_scail]; models: Wan2.1 SCAIL; open source; min ComfyUI 0.3.42; custom nodes: ComfyUI-WanAnimatePreprocess, ComfyUI-WanVideoWrapper, comfyui-kjnodes, comfyui-scail-pose, comfyui-videohelpersuite, comfyui_essentials; inputs: image, video; tags: Motion Control, Video - HeyGen Video 1.0: Reference to Video [api_heygen_video_1_r2v]; models: HeyGen; API service; min ComfyUI 0.38.1; inputs: image; tags: API, Reference to Video - HeyGen Video 1.0: Text to Video [api_heygen_video_1_t2v]; models: HeyGen; API service; min ComfyUI 0.38.1; tags: API, Text to Video - HeyGen: Talking Photo [api_heygen_talking_photo]; models: HeyGen; API service; min ComfyUI 0.28.1; inputs: image; tags: API, Image to Video, Lip Sync - VEED Fabric 1.0: Talking Photo [api_veed_fabric_1_0]; models: VEED; API service; min ComfyUI 0.43.0; inputs: audio, image; tags: API, Image to Video, Lip Sync - VEED Lipsync 2.0: Lip Sync [api_veed_lipsync_2_0]; models: VEED; API service; min ComfyUI 0.43.0; inputs: audio, video; tags: API, Lip Sync, Video Edit - Seedance 2.0 Mini: Reference to Video [api_seedance2_0_mini_r2v]; models: Seedance 2.0; API service; min ComfyUI 0.26.2; inputs: image; tags: API, Image to Video, Reference to Video - Seedance2.0 4K: Reference to Video [api_seedance2_0_r2v_4k]; models: Seedance 2.0; API service; min ComfyUI 0.26.2; inputs: image; tags: API, Image to Video, Reference to Video - Storyboard To Video - Seedance 2.0 [template_seedance2_storyboard_to_video]; models: Seedance 2.0; API service; min ComfyUI 0.21.1; inputs: image; tags: API, Image to Video - LTX-2.5 (Pro): Image to Video [api_ltx2_5_i2v]; models: LTX-2.5; API service; min ComfyUI 0.32.0; inputs: image; tags: API, Image to Video - LTX-2.5 (Pro): FLF2V [api_ltx2_5_flf2v]; models: LTX-2.5; API service; min ComfyUI 0.32.0; inputs: image; tags: API, FLF2V - Hunyuan Video 1.5 Image to Video [video_hunyuan_video_1.5_720p_i2v]; models: Hunyuan Video; source unstated; min ComfyUI 0.3.71; inputs: image; tags: Image to Video, Video - Hunyuan Video 1.5 Text to Video [video_hunyuan_video_1.5_720p_t2v]; models: Hunyuan Video; open source; min ComfyUI 0.3.71; tags: Text to Video, Video - FLUX 3 Video: Image to Video [api_bfl_flux3_i2v]; models: FLUX 3 Video; API service; min ComfyUI 0.30.2; inputs: image; tags: API, Image to Video - Wan2.7: Video Edit [api_wan2_7_video_edit]; models: Wan2.7; API service; min ComfyUI 0.18.4; inputs: image, video; tags: API, Video, Video Edit - Wan2.7: Image to Video [api_wan2_7_i2v]; models: Wan2.7; API service; min ComfyUI 0.18.4; inputs: image; tags: API, Image to Video, Video - Sync 3: Video Lip-Sync [api_sync_so_lip_sync_video]; models: Sync 3; API service; min ComfyUI 0.28.0; inputs: audio, video; tags: API, Lip Sync - Multi-Keyframe Video Stitching [templates-6-key-frames]; models: Wan2.2; open source; min ComfyUI 0.8.0; inputs: image; tags: FLF2V, Image to Video - Wan2.2-S2V Audio-Driven Video Generation [video_wan2_2_14B_s2v]; models: Wan2.2, Wan; source unstated; min ComfyUI 0.3.55; inputs: audio, image; tags: Video, Audio to Video; official tutorial linked - Wan 2.1 Text to Video [text_to_video_wan]; models: Wan2.1, Wan; source unstated; min ComfyUI 0.3.31; tags: Text to Video, Video; official tutorial linked - Wan2.1 VACE Outpainting [video_wan_vace_outpainting]; models: Wan2.1, Wan; source unstated; min ComfyUI 0.3.31; inputs: video; tags: Outpainting, Video; official tutorial linked - Causal Forcing: Image to Video [video_causal_forcing_i2v]; models: Wan2.1; open source; min ComfyUI 0.21.0; inputs: image; tags: Image to Video - Wan2.1 VACE Reference to Video [video_wan_vace_14B_ref2v]; models: Wan2.1, Wan; source unstated; min ComfyUI 0.8.0; inputs: image; tags: Video, Image to Video; official tutorial linked - Wan2.2 Animate, Character Animation and Replacement [video_wan2_2_14B_animate]; models: Wan, wan2.2 Animate; open source; min ComfyUI 0.8.0; custom nodes: ComfyUI-segment-anything-2, comfyui-kjnodes, comfyui_controlnet_aux; inputs: image, video; tags: Video, Image to Video; official tutorial linked - Wan 2.1 ControlNet [wan2.1_fun_control]; models: Wan2.1, Wan; source unstated; min ComfyUI 0.3.31; inputs: image, video; tags: Video to Video, Video; official tutorial linked - Wan2.1 VACE First-Last Frame [video_wan_vace_flf2v]; models: Wan2.1, Wan; open source; min ComfyUI 0.16.4; inputs: image; tags: FLF2V, Video; official tutorial linked - Wan Dancer: Music to Dance [video_wan_dancer]; models: Wan; open source; min ComfyUI 0.21.0; inputs: audio, image; tags: Audio to Video - Wan2.6: Image to Video [api_wan2_6_i2v]; models: Wan2.6, Wan; API service; min ComfyUI 0.3.60; inputs: image; tags: Image to Video, Video, API - Wan2.5: Image to Video [api_wan_image_to_video]; models: Wan2.5, Wan; API service; min ComfyUI 0.3.60; inputs: audio, image; tags: Image to Video, Video, API - Wan 2.2 14B Fun Camera Control [video_wan2_2_14B_fun_camera]; models: Wan2.2, Wan; source unstated; min ComfyUI 0.3.35; inputs: image; tags: Video to Video, Video; official tutorial linked - Wan 2.1 Fun Camera 14B [video_wan2.1_fun_camera_v1.1_14B]; models: Wan2.1, Wan; source unstated; min ComfyUI 0.3.35; inputs: image; tags: Video, Image to Video; official tutorial linked - Wan 2.1 Fun Camera 1.3B [video_wan2.1_fun_camera_v1.1_1.3B]; models: Wan2.1, Wan; source unstated; min ComfyUI 0.3.35; inputs: image; tags: Video, Image to Video; official tutorial linked - Gemini Omni Flash: Image to Video [api_google_gemini_omni_flash_i2v]; models: Gemini Omni; API service; min ComfyUI 0.28.3; inputs: image; tags: API, Image to Video - Gemini Omni Flash: Video Edit [api_google_gemini_omni_flash_video_edit]; models: Gemini Omni; API service; min ComfyUI 0.28.3; inputs: video; tags: API, Video Edit - Kandinsky 5.0 Video Lite Text to Video [video_kandinsky5_t2v]; models: Kandinsky; open source; min ComfyUI 0.4.0; tags: Text to Video, Video - Kling O1: Image to Video [api_kling_omni_i2v]; models: Kling O1; API service; min ComfyUI 0.8.0; inputs: image; tags: API, Video, Character Reference - Kling O1: Video to Video [api_kling_omni_v2v]; models: Kling O1; API service; min ComfyUI 0.8.0; inputs: image, video; tags: API, Character Reference, Video - Pruna P-Video 2: Text to Video [api_pruna_p_video_t2v]; models: P-Video-2; API service; min ComfyUI 0.36.0; tags: API, Text to Video - Luma Ray 3.2: Image to Video [api_luma_ray3_3_i2v]; models: Luma; API service; min ComfyUI 0.26.0; inputs: image; tags: Image to Video, API - Kling2.6: Motion Control [api_kling_motion_control]; models: Kling 2.6, Kling; API service; min ComfyUI 0.7.0; inputs: image, video; tags: Video, Motion Control, API - InfiniteTalk: Audio-Driven Full-Body Video Dubbing [video_wan2_1_infinitetalk]; models: Wan2.1 InfiniteTalk; open source; min ComfyUI 0.17.0; inputs: audio, image; tags: Audio to Video, Lip Sync, Video - Kling O1: Video Edit [api_kling_omni_edit_video]; models: Kling; API service; min ComfyUI 0.14.0; inputs: image, video; tags: Video, API, Video Edit, Text to Video, Image to Video - Kling2.6: Storytelling Videos with Audio [api_kling2_6_t2v]; models: Kling, Kling 2.6; API service; min ComfyUI 0.5.0; tags: API, Audio, Text to Video, Video - Kling2.6: Animate Images with Audio [api_kling2_6_i2v]; models: Kling 2.6, Kling; API service; min ComfyUI 0.5.0; inputs: image; tags: Image to Video, Video, API, Audio - MiniMax H3: FLF2V [api_minimax_h3_flf2v]; models: MiniMax H3; API service; min ComfyUI 0.30.0; inputs: image; tags: API, FLF2V, Video - MiniMax H3: Text to Video [api_minimax_h3_t2v]; models: MiniMax H3; API service; min ComfyUI 0.30.0; tags: Text to Video, API, Video - MiniMax H3 Turbo: Text to Video [api_minimax_h3_max_turbo_t2v]; models: MiniMax H3; API service; min ComfyUI 0.34.4; tags: API - Capybara: Video Edit [video_capybara_v0_1_video_edit]; models: Capybara; open source; min ComfyUI 0.8.0; inputs: video; tags: Video Edit - Capybara: Image to Video [video_capybara_v0_1_image_to_video]; models: Capybara; open source; min ComfyUI 0.3.71; inputs: image; tags: Image to Video, Video - Video Restyle [templates_shane_video_restyle]; models: Wan2.1 VACE; open source; min ComfyUI 0.3.16; custom nodes: ComfyUI-WanVideoWrapper, comfyui-depthanythingv2, comfyui-kjnodes, comfyui-videohelpersuite, comfyui_controlnet_aux; inputs: image, video; tags: Video, Video to Video - Seedance2.5 1080P: Text to Video [api_seedance2_5_t2v_1080p]; models: Seedance 2.5; API service; min ComfyUI 0.31.0; tags: API, Text to Video - PixVerse 6.0: Image to Video [api_pixverse6_i2v]; models: PixVerse; API service; inputs: image; tags: API, Image to Video - PixVerse 6.0: Reference to Video [api_pixverse6_r2v]; models: PixVerse; API service; min ComfyUI 0.34.0; inputs: image; tags: API, Reference to Video - PixVerse 6.0: Text to Video [api_pixverse6_t2v]; models: PixVerse; API service; tags: API, Text to Video - PixVerse V6 Max: Text to Video [api_pixverse_v6_max_t2v]; models: PixVerse; API service; min ComfyUI 0.42.5; tags: API, Text to Video - PixVerse V6 Max: Image to Video [api_pixverse_v6_max_i2v]; models: PixVerse; API service; min ComfyUI 0.42.5; inputs: image; tags: API, Image to Video - PixVerse: Text to Video [api_pixverse_t2v]; models: PixVerse; API service; min ComfyUI 0.3.32; tags: Text to Video, Video, API - Vidu Q2: FLF2V [api_vidu_q2_flf2v]; models: Vidu Q2; API service; min ComfyUI 0.9.0; inputs: image; tags: FLF2V, Video, API - Vidu Q2: Reference to Video [api_vidu_q2_r2v]; models: Vidu Q2, Vidu; API service; min ComfyUI 0.9.0; inputs: image; tags: Character Reference, Image to Video, API - Vidu Q3 Audio-Visual Video Generation [api_vidu_q3_text_to_video]; models: Vidu, Vidu Q3; API service; min ComfyUI 0.12.0; tags: API, Text to Video, Video - Vidu Q2: Image to Video [api_vidu_q2_i2v]; models: Vidu Q2, Vidu; API service; min ComfyUI 0.9.0; inputs: image; tags: Image to Video, API - Vidu Q1: Text to Video [api_vidu_text_to_video]; models: Vidu Q1, Vidu; API service; min ComfyUI 0.3.51; tags: Text to Video, Video, API - Vidu Q2: Text to Video [api_vidu_q2_t2v]; models: Vidu Q2, Vidu; API service; min ComfyUI 0.9.0; tags: API, Text to Video, Video - Vidu Q1: Image to Video [api_vidu_image_to_video]; models: Vidu Q1, Vidu; API service; min ComfyUI 0.3.51; inputs: image; tags: Image to Video, Video, API - Vidu Q1: Reference to Video [api_vidu_reference_to_video]; models: Vidu Q1, Vidu; API service; min ComfyUI 0.8.0; inputs: image; tags: Video, Image to Video, API - Vidu Q3 Image-to-Video with Audio [api_vidu_q3_image_to_video]; models: Vidu, Vidu Q3; API service; min ComfyUI 0.12.0; inputs: image; tags: API, Image to Video, Video Rights: the template index is MIT-licensed; models, API services, thumbnails and custom nodes carry their own terms, which were not reviewed here. Values are source-reported at this revision; templates were not run. Based on Comfy-Org/workflow_templates templates/index.json pinned to revision 3c2199b9362457b12b9c60c6cc303501526ebd62 and observed on 2026-10-27. Index metadata only: workflow bodies, previews, tutorials and model licences were not fetched or reviewed, and no template was run. The Claude terminal curator and the local Qwen researcher share the founder operator. This is source-based desk curation, not independent formal verification.

{
  "citations": [
    {
      "url": "https://raw.githubusercontent.com/Comfy-Org/workflow_templates/3c2199b9362457b12b9c60c6cc303501526ebd62/templates/index.json",
      "note": "Shared pinned index snapshot observed 2026-10-27; templates/index.json at 3c2199b9; category Video, Video part 1: 150 template entries (identifiers listed in the record); partition inventory in archive f966c9c1bb6669932c940f1aa4cbaf72a449512f20d6e0a9e7e8fb9739d9f8e4"
    }
  ]
}