{"id": "a7c4e2f9-6d1b-4b8e-9f3a-gmanski-flowlong", "revision": 0, "last_node_id": 31, "last_link_id": 37, "nodes": [{"id": 1, "type": "MarkdownNote", "pos": [-1600, -420], "size": [560, 1000], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [], "properties": {"Node name for S&R": "MarkdownNote"}, "widgets_values": ["## Gmanski Flow (Long)\n\n**One job, 10-30 seconds of video with continuous sound.** This is Gmanski Flow (Simple) with ComfyUI's native **MiniMax H3 Context Windows** (ComfyUI 0.44+): sampling runs in overlapping 124-frame windows that start on H3's 17-frame chunks, so picture and audio stay in sync across the whole clip and the windows blend (pyramid fusing + FreeNoise). No chunk files, no joins to colour-match.\n\n| You connect | Mode |\n|---|---|\n| Nothing | Text-to-video |\n| Only **First frame** | Image-to-video |\n| **First frame** + **Last frame** | First+last-frame-to-video |\n\n### Run it\n1. Edit the **prompt** on the H3 node (visual style, subject, action, camera, sound).\n2. Set **Duration (seconds)** - default 12 s. The frame count snaps to H3's 17n+5 grid. 10-15 s is the sweet spot; 30 s works but drifts more.\n3. Queue. Result: `output/video/Gmanski/gmanski_flow_long_00001.mp4`.\n\n### Optional: native refine (1.5x, sharper)\nThe grey **Refine** nodes are bypassed. Right-click each -> **Mode -> Always** to re-sample the finished clip at 1408x800 with the core **H3 latent upscaler** (no VAE round trip), 6 steps at denoise 0.4, inside the same context windows. A second file `gmanski_flow_long_refined_00001.mp4` is saved. Needs `gmanski-packs install minimax-h3-refine` (0.7 GB) and roughly doubles the time.\n\n**Sol-H3-VAE** (NVIDIA, 2.5-8x faster decode) is loaded but not wired: drag its VAE into the refine pass's **Decode picture** to try it. It cannot tile and some people see faint 128 px seams on smooth skin - judge at 4x crops.\n\n### Cost\n- **Download**: `minimax-h3-flow` (~43 GB) + `minimax-h3-refine` (0.7 GB + 2 GB Sol VAE).\n- **VRAM**: 48 GB+ for 12 s at 960x544; 96 GB for the refine at 20+ s.\n- **Time**: scales with duration (every window is a full pass). Enable the **Turbo LoRA** (Mode -> Always, scheduler steps 20 -> 8) for ~2x.\n\n### How it compares to Flow (Extend)\nFlow (Extend) chains takes on saved latents with our masked pin windows (works on any ComfyUI, one chunk per run). Flow (Long) does it in one pass on ComfyUI 0.44+. Both are ours; pick Long when the pod has the VRAM and you want one file out.\n\n### Models\n`gmanski-packs install minimax-h3-flow minimax-h3-refine`.\n"], "title": "Read me: Gmanski Flow (Long)", "color": "#432", "bgcolor": "#653"}, {"id": 2, "type": "LoadImage", "pos": [-1000, -420], "size": [320, 314], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": []}, {"name": "MASK", "type": "MASK", "links": []}], "properties": {"Node name for S&R": "LoadImage"}, "widgets_values": ["example.png", "image"], "title": "First frame (optional - connect to enable Image-to-Video)"}, {"id": 3, "type": "LoadImage", "pos": [-1000, -60], "size": [320, 314], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": []}, {"name": "MASK", "type": "MASK", "links": []}], "properties": {"Node name for S&R": "LoadImage"}, "widgets_values": ["example.png", "image"], "title": "Last frame (optional - connect too, for First+Last-Frame-to-Video)"}, {"id": 4, "type": "PrimitiveFloat", "pos": [-1000, 300], "size": [320, 60], "flags": {}, "order": 3, "mode": 0, "inputs": [{"name": "value", "type": "FLOAT", "link": null, "widget": {"name": "value"}}], "outputs": [{"name": "FLOAT", "type": "FLOAT", "links": [1]}], "properties": {"Node name for S&R": "PrimitiveFloat"}, "widgets_values": [12.0], "title": "Duration (seconds) - 10-30"}, {"id": 5, "type": "ComfyMathExpression", "pos": [-1000, 400], "size": [320, 90], "flags": {}, "order": 4, "mode": 0, "inputs": [{"name": "values.a", "type": "FLOAT,INT,BOOLEAN", "link": 1}], "outputs": [{"name": "FLOAT", "type": "FLOAT", "links": []}, {"name": "INT", "type": "INT", "links": [8]}, {"name": "BOOL", "type": "BOOLEAN", "links": []}], "properties": {"Node name for S&R": "ComfyMathExpression"}, "widgets_values": ["max(5, round(a * 24)) + (5 - (max(5, round(a * 24)) % 17)) % 17"], "title": "Frame count (17n+5)"}, {"id": 6, "type": "UNETLoader", "pos": [500, 900], "size": [440, 90], "flags": {}, "order": 5, "mode": 0, "inputs": [{"name": "unet_name", "type": "COMBO", "link": null, "widget": {"name": "unet_name"}}, {"name": "weight_dtype", "type": "COMBO", "link": null, "widget": {"name": "weight_dtype"}}], "outputs": [{"name": "MODEL", "type": "MODEL", "links": [2]}], "properties": {"Node name for S&R": "UNETLoader", "models": [{"name": "minimax_h3_fl2va_pruned_int8_convrot.safetensors", "url": "https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors", "directory": "diffusion_models"}]}, "widgets_values": ["minimax_h3_fl2va_pruned_int8_convrot.safetensors", "default"], "title": "MiniMax H3 flow checkpoint"}, {"id": 7, "type": "LoraLoaderModelOnly", "pos": [500, 1020], "size": [440, 90], "flags": {}, "order": 6, "mode": 4, "inputs": [{"name": "model", "type": "MODEL", "link": 2}, {"name": "lora_name", "type": "COMBO", "link": null, "widget": {"name": "lora_name"}}, {"name": "strength_model", "type": "FLOAT", "link": null, "widget": {"name": "strength_model"}}], "outputs": [{"name": "MODEL", "type": "MODEL", "links": [3]}], "properties": {"Node name for S&R": "LoraLoaderModelOnly", "models": [{"name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors", "url": "https://huggingface.co/lightx2v/Minimax-h3-Turbo/resolve/main/minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors", "directory": "loras"}]}, "widgets_values": ["minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors", 1.0], "title": "Turbo LoRA — bypassed by default, see readme"}, {"id": 8, "type": "MiniMaxH3SigmaShift", "pos": [500, 1140], "size": [300, 110], "flags": {}, "order": 7, "mode": 0, "inputs": [{"name": "model", "type": "MODEL", "link": 3}, {"name": "shift_video", "type": "FLOAT", "link": null, "widget": {"name": "shift_video"}}, {"name": "shift_audio", "type": "FLOAT", "link": null, "widget": {"name": "shift_audio"}}], "outputs": [{"name": "MODEL", "type": "MODEL", "links": [4]}], "properties": {"Node name for S&R": "MiniMaxH3SigmaShift"}, "widgets_values": [12, 3], "title": "Sigma shift"}, {"id": 9, "type": "MiniMaxH3ContextWindows", "pos": [500, 1250], "size": [380, 180], "flags": {}, "order": 8, "mode": 0, "inputs": [{"name": "model", "type": "MODEL", "link": 4}, {"name": "context_length", "type": "INT", "link": null, "widget": {"name": "context_length"}}, {"name": "context_overlap", "type": "INT", "link": null, "widget": {"name": "context_overlap"}}, {"name": "fuse_method", "type": "COMBO", "link": null, "widget": {"name": "fuse_method"}}, {"name": "freenoise", "type": "BOOLEAN", "link": null, "widget": {"name": "freenoise"}}, {"name": "split_conds_to_windows", "type": "BOOLEAN", "link": null, "widget": {"name": "split_conds_to_windows"}}], "outputs": [{"name": "MODEL", "type": "MODEL", "links": [5, 9, 25]}], "properties": {"Node name for S&R": "MiniMaxH3ContextWindows"}, "widgets_values": [124, 39, "pyramid", true, false], "title": "Context windows (124 frames, overlap 39) - ComfyUI 0.44+"}, {"id": 10, "type": "CLIPLoader", "pos": [500, 1280], "size": [440, 110], "flags": {}, "order": 9, "mode": 0, "inputs": [{"name": "clip_name", "type": "COMBO", "link": null, "widget": {"name": "clip_name"}}, {"name": "type", "type": "COMBO", "link": null, "widget": {"name": "type"}}, {"name": "device", "type": "COMBO", "link": null, "widget": {"name": "device"}}], "outputs": [{"name": "CLIP", "type": "CLIP", "links": [6]}], "properties": {"Node name for S&R": "CLIPLoader", "models": [{"name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors", "url": "https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors", "directory": "text_encoders"}]}, "widgets_values": ["qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors", "minimax", "default"], "title": "MiniMax H3 text encoder"}, {"id": 11, "type": "VAELoader", "pos": [500, 1420], "size": [440, 60], "flags": {}, "order": 10, "mode": 0, "inputs": [{"name": "vae_name", "type": "COMBO", "link": null, "widget": {"name": "vae_name"}}], "outputs": [{"name": "VAE", "type": "VAE", "links": [7, 17, 32]}], "properties": {"Node name for S&R": "VAELoader", "models": [{"name": "minimax_h3_video_vae_fp16.safetensors", "url": "https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors", "directory": "vae"}]}, "widgets_values": ["minimax_h3_video_vae_fp16.safetensors"], "title": "MiniMax H3 video VAE"}, {"id": 12, "type": "VAELoader", "pos": [500, 1510], "size": [440, 60], "flags": {}, "order": 11, "mode": 0, "inputs": [{"name": "vae_name", "type": "COMBO", "link": null, "widget": {"name": "vae_name"}}], "outputs": [{"name": "VAE", "type": "VAE", "links": [19, 34]}], "properties": {"Node name for S&R": "VAELoader", "models": [{"name": "minimax_h3_audio_vae_fp32.safetensors", "url": "https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors", "directory": "vae"}]}, "widgets_values": ["minimax_h3_audio_vae_fp32.safetensors"], "title": "MiniMax H3 audio VAE"}, {"id": 13, "type": "KSamplerSelect", "pos": [500, 1600], "size": [300, 60], "flags": {}, "order": 12, "mode": 0, "inputs": [{"name": "sampler_name", "type": "COMBO", "link": null, "widget": {"name": "sampler_name"}}], "outputs": [{"name": "SAMPLER", "type": "SAMPLER", "links": [13, 28]}], "properties": {"Node name for S&R": "KSamplerSelect"}, "widgets_values": ["res_multistep"], "title": "Sampler (shared)"}, {"id": 14, "type": "BasicScheduler", "pos": [500, 1680], "size": [300, 130], "flags": {}, "order": 13, "mode": 0, "inputs": [{"name": "model", "type": "MODEL", "link": 5}, {"name": "scheduler", "type": "COMBO", "link": null, "widget": {"name": "scheduler"}}, {"name": "steps", "type": "INT", "link": null, "widget": {"name": "steps"}}, {"name": "denoise", "type": "FLOAT", "link": null, "widget": {"name": "denoise"}}], "outputs": [{"name": "SIGMAS", "type": "SIGMAS", "links": [14]}], "properties": {"Node name for S&R": "BasicScheduler"}, "widgets_values": ["simple", 20, 1.0], "title": "Scheduler (20 steps — 8 if turbo LoRA enabled)"}, {"id": 15, "type": "MiniMaxH3ImageToVideo", "pos": [0, -420], "size": [520, 320], "flags": {}, "order": 14, "mode": 0, "inputs": [{"name": "clip", "type": "CLIP", "link": 6}, {"name": "vae", "type": "VAE", "link": 7}, {"name": "first_frame", "type": "IMAGE", "link": null}, {"name": "last_frame", "type": "IMAGE", "link": null}, {"name": "prompt", "type": "STRING", "link": null, "widget": {"name": "prompt"}}, {"name": "width", "type": "INT", "link": null, "widget": {"name": "width"}}, {"name": "height", "type": "INT", "link": null, "widget": {"name": "height"}}, {"name": "length", "type": "INT", "link": 8, "widget": {"name": "length"}}], "outputs": [{"name": "positive", "type": "CONDITIONING", "links": [10]}, {"name": "LATENT", "type": "LATENT", "links": [15]}], "properties": {"Node name for S&R": "MiniMaxH3ImageToVideo"}, "widgets_values": ["cinematic photorealistic style. A woman in a red coat walks along a rainy city street at night holding a clear umbrella, neon signs reflecting in the wet pavement. Steady rain, distant traffic hum, soft footsteps. Plain, unbranded clothing and signage: no logos, emblems, brand names, readable text or watermarks. Camera: static medium shot, slow push in.", 960, 544, 294], "title": "H3 node - prompt, size, and (optionally wired) keyframes"}, {"id": 16, "type": "RandomNoise", "pos": [600, -420], "size": [290, 82], "flags": {}, "order": 15, "mode": 0, "inputs": [{"name": "noise_seed", "type": "INT", "link": null, "widget": {"name": "noise_seed"}}], "outputs": [{"name": "NOISE", "type": "NOISE", "links": [11, 26]}], "properties": {"Node name for S&R": "RandomNoise"}, "widgets_values": [12345, "randomize"], "title": "Seed (shared by both passes)"}, {"id": 17, "type": "BasicGuider", "pos": [600, -300], "size": [290, 46], "flags": {}, "order": 16, "mode": 0, "inputs": [{"name": "model", "type": "MODEL", "link": 9}, {"name": "conditioning", "type": "CONDITIONING", "link": 10}], "outputs": [{"name": "GUIDER", "type": "GUIDER", "links": [12, 27]}], "properties": {"Node name for S&R": "BasicGuider"}, "widgets_values": [], "title": "Guider"}, {"id": 18, "type": "SamplerCustomAdvanced", "pos": [960, -420], "size": [300, 200], "flags": {}, "order": 17, "mode": 0, "inputs": [{"name": "noise", "type": "NOISE", "link": 11}, {"name": "guider", "type": "GUIDER", "link": 12}, {"name": "sampler", "type": "SAMPLER", "link": 13}, {"name": "sigmas", "type": "SIGMAS", "link": 14}, {"name": "latent_image", "type": "LATENT", "link": 15}], "outputs": [{"name": "LATENT", "type": "LATENT", "links": [16, 18, 24]}], "properties": {"Node name for S&R": "SamplerCustomAdvanced"}, "widgets_values": [], "title": "Sample (windowed)"}, {"id": 19, "type": "VAEDecode", "pos": [1320, -420], "size": [300, 46], "flags": {}, "order": 18, "mode": 0, "inputs": [{"name": "samples", "type": "LATENT", "link": 16}, {"name": "vae", "type": "VAE", "link": 17}], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": [20]}], "properties": {"Node name for S&R": "VAEDecode"}, "widgets_values": [], "title": "Decode picture"}, {"id": 20, "type": "VAEDecodeAudio", "pos": [1320, -340], "size": [300, 46], "flags": {}, "order": 19, "mode": 0, "inputs": [{"name": "samples", "type": "LATENT", "link": 18}, {"name": "vae", "type": "VAE", "link": 19}], "outputs": [{"name": "AUDIO", "type": "AUDIO", "links": [21]}], "properties": {"Node name for S&R": "VAEDecodeAudio"}, "widgets_values": [], "title": "Decode sound (H3's own native audio)"}, {"id": 21, "type": "CreateVideo", "pos": [1680, -420], "size": [280, 126], "flags": {}, "order": 20, "mode": 0, "inputs": [{"name": "images", "type": "IMAGE", "link": 20}, {"name": "audio", "type": "AUDIO", "link": 21}, {"name": "fps", "type": "FLOAT", "link": null, "widget": {"name": "fps"}}, {"name": "bit_depth", "type": "COMBO", "link": null, "widget": {"name": "bit_depth"}}], "outputs": [{"name": "VIDEO", "type": "VIDEO", "links": [22]}], "properties": {"Node name for S&R": "CreateVideo"}, "widgets_values": [24, 8, "sRGB"], "title": "Join into a video"}, {"id": 22, "type": "SaveVideo", "pos": [1680, -260], "size": [280, 200], "flags": {}, "order": 21, "mode": 0, "inputs": [{"name": "video", "type": "VIDEO", "link": 22}, {"name": "filename_prefix", "type": "STRING", "link": null, "widget": {"name": "filename_prefix"}}, {"name": "format", "type": "COMFY_DYNAMICCOMBO_V3", "link": null, "widget": {"name": "format"}}, {"name": "codec", "type": "COMFY_DYNAMICCOMBO_V3", "link": null, "widget": {"name": "codec"}}], "outputs": [], "properties": {"Node name for S&R": "SaveVideo"}, "widgets_values": ["video/Gmanski/gmanski_flow_long", "auto", "auto", "auto"], "title": "Save"}, {"id": 23, "type": "LatentUpscaleModelLoader", "pos": [0, 200], "size": [420, 60], "flags": {}, "order": 22, "mode": 4, "inputs": [{"name": "model_name", "type": "COMBO", "link": null, "widget": {"name": "model_name"}}], "outputs": [{"name": "LATENT_UPSCALE_MODEL", "type": "LATENT_UPSCALE_MODEL", "links": [23]}], "properties": {"Node name for S&R": "LatentUpscaleModelLoader", "models": [{"name": "minimax_h3_latent_upscaler_3d_fp16.safetensors", "url": "https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler/resolve/main/minimax_h3_latent_upscaler_3d_conv_v1/minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors", "directory": "latent_upscale_models"}]}, "widgets_values": ["minimax_h3_latent_upscaler_3d_fp16.safetensors"], "title": "Refine 1/6: H3 latent upscaler (core) - bypassed"}, {"id": 24, "type": "MiniMaxH3LatentUpscaleWithModel", "pos": [0, 300], "size": [420, 110], "flags": {}, "order": 23, "mode": 4, "inputs": [{"name": "model", "type": "LATENT_UPSCALE_MODEL", "link": 23}, {"name": "samples", "type": "LATENT", "link": 24}, {"name": "width", "type": "INT", "link": null, "widget": {"name": "width"}}, {"name": "height", "type": "INT", "link": null, "widget": {"name": "height"}}], "outputs": [{"name": "LATENT", "type": "LATENT", "links": [30]}], "properties": {"Node name for S&R": "MiniMaxH3LatentUpscaleWithModel"}, "widgets_values": [1408, 800], "title": "Refine 2/6: upscale latent to 1408x800"}, {"id": 25, "type": "BasicScheduler", "pos": [0, 450], "size": [300, 130], "flags": {}, "order": 24, "mode": 4, "inputs": [{"name": "model", "type": "MODEL", "link": 25}, {"name": "scheduler", "type": "COMBO", "link": null, "widget": {"name": "scheduler"}}, {"name": "steps", "type": "INT", "link": null, "widget": {"name": "steps"}}, {"name": "denoise", "type": "FLOAT", "link": null, "widget": {"name": "denoise"}}], "outputs": [{"name": "SIGMAS", "type": "SIGMAS", "links": [29]}], "properties": {"Node name for S&R": "BasicScheduler"}, "widgets_values": ["simple", 6, 0.4], "title": "Refine 3/6: 6 steps at denoise 0.4"}, {"id": 26, "type": "SamplerCustomAdvanced", "pos": [500, 450], "size": [300, 200], "flags": {}, "order": 25, "mode": 4, "inputs": [{"name": "noise", "type": "NOISE", "link": 26}, {"name": "guider", "type": "GUIDER", "link": 27}, {"name": "sampler", "type": "SAMPLER", "link": 28}, {"name": "sigmas", "type": "SIGMAS", "link": 29}, {"name": "latent_image", "type": "LATENT", "link": 30}], "outputs": [{"name": "LATENT", "type": "LATENT", "links": [31, 33]}], "properties": {"Node name for S&R": "SamplerCustomAdvanced"}, "widgets_values": [], "title": "Refine 4/6: re-sample (same windows, guider, seed)"}, {"id": 27, "type": "VAELoader", "pos": [960, 700], "size": [420, 60], "flags": {}, "order": 26, "mode": 4, "inputs": [{"name": "vae_name", "type": "COMBO", "link": null, "widget": {"name": "vae_name"}}], "outputs": [{"name": "VAE", "type": "VAE", "links": []}], "properties": {"Node name for S&R": "VAELoader", "models": [{"name": "minimax_h3_sol_vae_int8_convrot.safetensors", "url": "https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_sol_vae_int8_convrot.safetensors", "directory": "vae"}]}, "widgets_values": ["minimax_h3_sol_vae_int8_convrot.safetensors"], "title": "Sol-H3-VAE fast decoder (not wired - try it on Decode picture below)"}, {"id": 28, "type": "VAEDecode", "pos": [960, 450], "size": [300, 46], "flags": {}, "order": 27, "mode": 4, "inputs": [{"name": "samples", "type": "LATENT", "link": 31}, {"name": "vae", "type": "VAE", "link": 32}], "outputs": [{"name": "IMAGE", "type": "IMAGE", "links": [35]}], "properties": {"Node name for S&R": "VAEDecode"}, "widgets_values": [], "title": "Refine 5/6: decode picture"}, {"id": 29, "type": "VAEDecodeAudio", "pos": [960, 530], "size": [300, 46], "flags": {}, "order": 28, "mode": 4, "inputs": [{"name": "samples", "type": "LATENT", "link": 33}, {"name": "vae", "type": "VAE", "link": 34}], "outputs": [{"name": "AUDIO", "type": "AUDIO", "links": [36]}], "properties": {"Node name for S&R": "VAEDecodeAudio"}, "widgets_values": [], "title": "Refine 5/6: decode sound"}, {"id": 30, "type": "CreateVideo", "pos": [1320, 450], "size": [280, 126], "flags": {}, "order": 29, "mode": 4, "inputs": [{"name": "images", "type": "IMAGE", "link": 35}, {"name": "audio", "type": "AUDIO", "link": 36}, {"name": "fps", "type": "FLOAT", "link": null, "widget": {"name": "fps"}}, {"name": "bit_depth", "type": "COMBO", "link": null, "widget": {"name": "bit_depth"}}], "outputs": [{"name": "VIDEO", "type": "VIDEO", "links": [37]}], "properties": {"Node name for S&R": "CreateVideo"}, "widgets_values": [24, 8, "sRGB"], "title": "Refine 6/6: join"}, {"id": 31, "type": "SaveVideo", "pos": [1680, 450], "size": [280, 200], "flags": {}, "order": 30, "mode": 4, "inputs": [{"name": "video", "type": "VIDEO", "link": 37}, {"name": "filename_prefix", "type": "STRING", "link": null, "widget": {"name": "filename_prefix"}}, {"name": "format", "type": "COMFY_DYNAMICCOMBO_V3", "link": null, "widget": {"name": "format"}}, {"name": "codec", "type": "COMFY_DYNAMICCOMBO_V3", "link": null, "widget": {"name": "codec"}}], "outputs": [], "properties": {"Node name for S&R": "SaveVideo"}, "widgets_values": ["video/Gmanski/gmanski_flow_long_refined", "auto", "auto", "auto"], "title": "Refine 6/6: save (*_refined)"}], "links": [[1, 4, 0, 5, 0, "FLOAT"], [2, 6, 0, 7, 0, "MODEL"], [3, 7, 0, 8, 0, "MODEL"], [4, 8, 0, 9, 0, "MODEL"], [5, 9, 0, 14, 0, "MODEL"], [6, 10, 0, 15, 0, "CLIP"], [7, 11, 0, 15, 1, "VAE"], [8, 5, 1, 15, 7, "INT"], [9, 9, 0, 17, 0, "MODEL"], [10, 15, 0, 17, 1, "CONDITIONING"], [11, 16, 0, 18, 0, "NOISE"], [12, 17, 0, 18, 1, "GUIDER"], [13, 13, 0, 18, 2, "SAMPLER"], [14, 14, 0, 18, 3, "SIGMAS"], [15, 15, 1, 18, 4, "LATENT"], [16, 18, 0, 19, 0, "LATENT"], [17, 11, 0, 19, 1, "VAE"], [18, 18, 0, 20, 0, "LATENT"], [19, 12, 0, 20, 1, "VAE"], [20, 19, 0, 21, 0, "IMAGE"], [21, 20, 0, 21, 1, "AUDIO"], [22, 21, 0, 22, 0, "VIDEO"], [23, 23, 0, 24, 0, "LATENT_UPSCALE_MODEL"], [24, 18, 0, 24, 1, "LATENT"], [25, 9, 0, 25, 0, "MODEL"], [26, 16, 0, 26, 0, "NOISE"], [27, 17, 0, 26, 1, "GUIDER"], [28, 13, 0, 26, 2, "SAMPLER"], [29, 25, 0, 26, 3, "SIGMAS"], [30, 24, 0, 26, 4, "LATENT"], [31, 26, 0, 28, 0, "LATENT"], [32, 11, 0, 28, 1, "VAE"], [33, 26, 0, 29, 0, "LATENT"], [34, 12, 0, 29, 1, "VAE"], [35, 28, 0, 30, 0, "IMAGE"], [36, 29, 0, 30, 1, "AUDIO"], [37, 30, 0, 31, 0, "VIDEO"]], "groups": [], "config": {}, "extra": {"ds": {"scale": 0.62, "offset": [1480, 420]}, "gmanski_template": "flow-long", "generator": "scripts/build_gmanski_flow_long_workflow.py", "source": "https://gmanski.com/workflows/flow-long"}, "version": 0.4}