{ "id": "52b6cc9f-a7d2-4466-8767-9354a8b278ce", "revision": 0, "last_node_id": 65, "last_link_id": 99, "nodes": [ { "id": 41, "type": "MarkdownNote", "pos": [ -680, 4870 ], "size": [ 580, 810 ], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [], "title": "Note: PixelDiT", "properties": {}, "widgets_values": [ "## PixelDiT Text-to-Image\n\nNVIDIA's **PixelDiT** is a pixel-space diffusion transformer for 1024px text-to-image generation.\n\n### Links\n\n- **ComfyUI support PR:** [Comfy-Org/ComfyUI#14103](https://github.com/Comfy-Org/ComfyUI/pull/14103) — merged 2026-05-27; adds PixelDiT T2I and PiD support\n- **Official model:** [nvidia/PixelDiT-1300M-1024px](https://huggingface.co/nvidia/PixelDiT-1300M-1024px)\n- **ComfyUI weights:** [Comfy-Org/PixelDiT](https://huggingface.co/Comfy-Org/PixelDiT)\n- **Subgraph:** [docs.comfy.org — Subgraph](https://docs.comfy.org/interface/features/subgraph)\n\n### Model highlights\n\n- **VAE-free** — generates directly in pixel space; no traditional VAE encode/decode\n- **Dual-level DiT** — patch-level DiT + pixel-level DiT\n- **MM-DiT fusion** — joint attention between text and image tokens\n- **Text encoder** — Gemma-2-2B-IT\n- **Multi aspect ratio** — 1024px base resolution; supports several aspect ratios\n- **Parameters** — ~1.3B\n- **License** — NSCLv1 (non-commercial research/evaluation only)\n\n### Workflow layout\n\n`ResolutionSelector` → [subgraph](https://docs.comfy.org/interface/features/subgraph) **Text to Image (PixelDiT)** → `SaveImage`\n\nMost generation settings live inside the [subgraph](https://docs.comfy.org/interface/features/subgraph). On the main canvas you mainly adjust resolution outside the [subgraph](https://docs.comfy.org/interface/features/subgraph) and the exposed [subgraph](https://docs.comfy.org/interface/features/subgraph) widgets below." ], "color": "#222", "bgcolor": "#000" }, { "id": 43, "type": "SaveImage", "pos": [ 750, 4880 ], "size": [ 620, 570 ], "flags": {}, "order": 4, "mode": 0, "inputs": [ { "name": "images", "type": "IMAGE", "link": 77 } ], "outputs": [], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "SaveImage" }, "widgets_values": [ "PixelDiT" ] }, { "id": 44, "type": "ef85a5af-0944-4f72-bffd-7d6d9941f33c", "pos": [ 240, 4880 ], "size": [ 470, 560 ], "flags": {}, "order": 3, "mode": 0, "inputs": [ { "label": "positive_prompt", "name": "text", "type": "STRING", "widget": { "name": "text" }, "link": null }, { "label": "negative_prompt", "name": "text_1", "type": "STRING", "widget": { "name": "text_1" }, "link": null }, { "name": "width", "type": "INT", "widget": { "name": "width" }, "link": 85 }, { "name": "height", "type": "INT", "widget": { "name": "height" }, "link": 86 } ], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 77 ] } ], "properties": { "proxyWidgets": [ [ "6", "text" ], [ "30", "text" ], [ "31", "width" ], [ "31", "height" ], [ "42", "seed" ], [ "2", "unet_name" ], [ "9", "clip_name" ] ], "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65 }, "widgets_values": [] }, { "id": 46, "type": "ResolutionSelector", "pos": [ -70, 5210 ], "size": [ 270, 170 ], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [ { "name": "width", "type": "INT", "links": [ 85 ] }, { "name": "height", "type": "INT", "links": [ 86 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "ResolutionSelector" }, "widgets_values": [ "1:1 (Square)", 1 ] }, { "id": 65, "type": "MarkdownNote", "pos": [ -1220, 4870 ], "size": [ 500, 790 ], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [], "title": "Note: Model Links", "properties": {}, "widgets_values": [ "Guide: [Subgraph](https://docs.comfy.org/interface/features/subgraph)\n\n## Model Links (for Local Users)\n\n**text_encoders**\n\n- [gemma_2_2b_it_elm_bf16.safetensors](https://huggingface.co/Comfy-Org/PixelDiT/resolve/main/text_encoders/gemma_2_2b_it_elm_bf16.safetensors)\n\n**diffusion_models**\n\n- [pixeldit_1300m_1024px_bf16.safetensors](https://huggingface.co/Comfy-Org/PixelDiT/resolve/main/diffusion_models/pixeldit_1300m_1024px_bf16.safetensors)\n\n\n## Model Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ └── gemma_2_2b_it_elm_bf16.safetensors\n│ └── 📂 diffusion_models/\n│ └── pixeldit_1300m_1024px_bf16.safetensors\n```\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n" ], "color": "#222", "bgcolor": "#000" } ], "links": [ [ 77, 44, 0, 43, 0, "IMAGE" ], [ 85, 46, 0, 44, 2, "INT" ], [ 86, 46, 1, 44, 3, "INT" ] ], "groups": [], "definitions": { "subgraphs": [ { "id": "ef85a5af-0944-4f72-bffd-7d6d9941f33c", "version": 1, "state": { "lastGroupId": 3, "lastNodeId": 65, "lastLinkId": 99, "lastRerouteId": 0 }, "revision": 0, "config": {}, "name": "Text to Image (PixelDiT)", "inputNode": { "id": -10, "bounding": [ -420, 5270, 143.044921875, 188 ] }, "outputNode": { "id": -20, "bounding": [ 1610, 5136, 128, 68 ] }, "inputs": [ { "id": "21c3bfc1-0716-46cb-a9c5-806cb91a0f33", "name": "text", "type": "STRING", "linkIds": [ 78 ], "label": "positive_prompt", "pos": [ -300.955078125, 5294 ] }, { "id": "9197794c-e750-4f8a-a7ef-ca1f46b2c39e", "name": "text_1", "type": "STRING", "linkIds": [ 79 ], "label": "negative_prompt", "pos": [ -300.955078125, 5314 ] }, { "id": "e8a6081b-0e92-42e9-b439-535df7d0a9aa", "name": "width", "type": "INT", "linkIds": [ 98 ], "pos": [ -300.955078125, 5334 ] }, { "id": "937caea0-d19b-48eb-a2a0-2623572a64ef", "name": "height", "type": "INT", "linkIds": [ 99 ], "pos": [ -300.955078125, 5354 ] }, { "id": "8db6bed4-ed0b-487b-be94-643e666f6985", "name": "seed", "type": "INT", "linkIds": [ 82 ], "pos": [ -300.955078125, 5374 ] }, { "id": "8ef2cd26-7240-4086-a176-bdee446de969", "name": "unet_name", "type": "COMBO", "linkIds": [ 83 ], "pos": [ -300.955078125, 5394 ] }, { "id": "7839f3b1-4d4b-4cfa-8d5b-5dbaf30a4cd1", "name": "clip_name", "type": "COMBO", "linkIds": [ 84 ], "pos": [ -300.955078125, 5414 ] } ], "outputs": [ { "id": "2a015ba4-1fc8-4c29-a87d-e8d50958debc", "name": "IMAGE", "type": "IMAGE", "linkIds": [ 76 ], "localized_name": "IMAGE", "pos": [ 1634, 5160 ] } ], "widgets": [], "nodes": [ { "id": 42, "type": "KSampler", "pos": [ 1000, 4810 ], "size": [ 270, 530 ], "flags": {}, "order": 7, "mode": 0, "inputs": [ { "localized_name": "model", "name": "model", "type": "MODEL", "link": 71 }, { "localized_name": "positive", "name": "positive", "type": "CONDITIONING", "link": 72 }, { "localized_name": "negative", "name": "negative", "type": "CONDITIONING", "link": 73 }, { "localized_name": "latent_image", "name": "latent_image", "type": "LATENT", "link": 74 }, { "localized_name": "seed", "name": "seed", "type": "INT", "widget": { "name": "seed" }, "link": 82 } ], "outputs": [ { "localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [ 75 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "KSampler" }, "widgets_values": [ 59233627785266, "randomize", 30, 4, "er_sde", "simple", 1 ] }, { "id": 30, "type": "CLIPTextEncode", "pos": [ 510, 5360 ], "size": [ 410, 200 ], "flags": {}, "order": 5, "mode": 0, "inputs": [ { "localized_name": "clip", "name": "clip", "type": "CLIP", "link": 55 }, { "localized_name": "text", "name": "text", "type": "STRING", "widget": { "name": "text" }, "link": 79 } ], "outputs": [ { "localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [ 73 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "CLIPTextEncode" }, "widgets_values": [ "low quality, worst quality, over-saturated, blurry, deformed, watermark" ], "color": "#223", "bgcolor": "#335" }, { "id": 15, "type": "VAEDecode", "pos": [ 1310, 4820 ], "size": [ 230, 100 ], "flags": { "collapsed": false }, "order": 4, "mode": 0, "inputs": [ { "localized_name": "samples", "name": "samples", "type": "LATENT", "link": 75 }, { "localized_name": "vae", "name": "vae", "type": "VAE", "link": 14 } ], "outputs": [ { "localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [ 76 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "VAEDecode" }, "widgets_values": [], "color": "#323", "bgcolor": "#535" }, { "id": 16, "type": "VAELoader", "pos": [ 1310, 4970 ], "size": [ 240, 110 ], "flags": { "collapsed": false }, "order": 0, "mode": 0, "inputs": [], "outputs": [ { "localized_name": "VAE", "name": "VAE", "type": "VAE", "links": [ 14 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "VAELoader" }, "widgets_values": [ "pixel_space" ], "color": "#323", "bgcolor": "#535" }, { "id": 9, "type": "CLIPLoader", "pos": [ 10, 5050 ], "size": [ 440, 170 ], "flags": {}, "order": 3, "mode": 0, "inputs": [ { "localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": { "name": "clip_name" }, "link": 84 } ], "outputs": [ { "localized_name": "CLIP", "name": "CLIP", "type": "CLIP", "links": [ 8, 55 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "CLIPLoader", "models": [ { "name": "gemma_2_2b_it_elm_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/PixelDiT/resolve/main/text_encoders/gemma_2_2b_it_elm_bf16.safetensors", "directory": "text_encoders" } ] }, "widgets_values": [ "gemma_2_2b_it_elm_bf16.safetensors", "pixeldit", "default" ] }, { "id": 2, "type": "UNETLoader", "pos": [ 20, 4840 ], "size": [ 420, 140 ], "flags": {}, "order": 1, "mode": 0, "inputs": [ { "localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": { "name": "unet_name" }, "link": 83 } ], "outputs": [ { "localized_name": "MODEL", "name": "MODEL", "type": "MODEL", "links": [ 71 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "UNETLoader", "models": [ { "name": "pixeldit_1300m_1024px_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/PixelDiT/resolve/main/diffusion_models/pixeldit_1300m_1024px_bf16.safetensors", "directory": "diffusion_models" } ] }, "widgets_values": [ "pixeldit_1300m_1024px_bf16.safetensors", "default" ] }, { "id": 31, "type": "EmptyChromaRadianceLatentImage", "pos": [ 40, 5400 ], "size": [ 360, 170 ], "flags": {}, "order": 6, "mode": 0, "inputs": [ { "localized_name": "width", "name": "width", "type": "INT", "widget": { "name": "width" }, "link": 98 }, { "localized_name": "height", "name": "height", "type": "INT", "widget": { "name": "height" }, "link": 99 } ], "outputs": [ { "localized_name": "LATENT", "name": "LATENT", "type": "LATENT", "links": [ 74 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "EmptyChromaRadianceLatentImage" }, "widgets_values": [ 1024, 1024, 1 ], "color": "#323", "bgcolor": "#535" }, { "id": 6, "type": "CLIPTextEncode", "pos": [ 510, 4840 ], "size": [ 410, 460 ], "flags": {}, "order": 2, "mode": 0, "inputs": [ { "localized_name": "clip", "name": "clip", "type": "CLIP", "link": 8 }, { "localized_name": "text", "name": "text", "type": "STRING", "widget": { "name": "text" }, "link": 78 } ], "outputs": [ { "localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING", "links": [ 72 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.22.0", "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "CLIPTextEncode" }, "widgets_values": [ "A surreal architectural scene featuring a woman in a flowing white dress walking away from the viewer through a narrow canyon of smooth, organic beige rock formations. The architecture resembles fluid sandstone or sculpted clay with undulating curves and soft edges. Bright sunlight streams from above, casting sharp shadows on the ground and illuminating the textured surfaces of the walls. The sky is a clear, deep blue visible at the top of the frame. The composition uses leading lines formed by the canyon walls to draw the eye toward the figure in the distance. High-quality photorealistic rendering with 8k resolution, cinematic lighting, dramatic contrast between light and shadow, and a sense of scale emphasizing the grandeur of the environment." ], "color": "#232", "bgcolor": "#353" } ], "groups": [ { "id": 1, "title": "Model", "bounding": [ 0, 4750, 460, 520 ], "color": "#3f789e", "flags": {} }, { "id": 2, "title": "Prompt", "bounding": [ 490, 4750, 460, 840 ], "color": "#3f789e", "flags": {} }, { "id": 3, "title": "Size", "bounding": [ 0, 5300, 460, 290 ], "color": "#3f789e", "flags": {} } ], "links": [ { "id": 71, "origin_id": 2, "origin_slot": 0, "target_id": 42, "target_slot": 0, "type": "MODEL" }, { "id": 72, "origin_id": 6, "origin_slot": 0, "target_id": 42, "target_slot": 1, "type": "CONDITIONING" }, { "id": 73, "origin_id": 30, "origin_slot": 0, "target_id": 42, "target_slot": 2, "type": "CONDITIONING" }, { "id": 74, "origin_id": 31, "origin_slot": 0, "target_id": 42, "target_slot": 3, "type": "LATENT" }, { "id": 55, "origin_id": 9, "origin_slot": 0, "target_id": 30, "target_slot": 0, "type": "CLIP" }, { "id": 75, "origin_id": 42, "origin_slot": 0, "target_id": 15, "target_slot": 0, "type": "LATENT" }, { "id": 14, "origin_id": 16, "origin_slot": 0, "target_id": 15, "target_slot": 1, "type": "VAE" }, { "id": 8, "origin_id": 9, "origin_slot": 0, "target_id": 6, "target_slot": 0, "type": "CLIP" }, { "id": 76, "origin_id": 15, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE" }, { "id": 78, "origin_id": -10, "origin_slot": 0, "target_id": 6, "target_slot": 1, "type": "STRING" }, { "id": 79, "origin_id": -10, "origin_slot": 1, "target_id": 30, "target_slot": 1, "type": "STRING" }, { "id": 82, "origin_id": -10, "origin_slot": 4, "target_id": 42, "target_slot": 4, "type": "INT" }, { "id": 83, "origin_id": -10, "origin_slot": 5, "target_id": 2, "target_slot": 0, "type": "COMBO" }, { "id": 84, "origin_id": -10, "origin_slot": 6, "target_id": 9, "target_slot": 0, "type": "COMBO" }, { "id": 98, "origin_id": -10, "origin_slot": 2, "target_id": 31, "target_slot": 0, "type": "INT" }, { "id": 99, "origin_id": -10, "origin_slot": 3, "target_id": 31, "target_slot": 1, "type": "INT" } ], "extra": {} } ] }, "config": {}, "extra": { "ds": { "scale": 0.5517281167157211, "offset": [ 1773.561570420257, -4085.1354324970202 ] }, "frontendVersion": "1.44.19", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true }, "version": 0.4 }