等距柱狀投影HDR天空盒產生器
使用提示詞產生一個環境,並產生一張等距柱狀投影的HDR圖像,用作遊戲開發中的天空盒或lookdev。
工作流程內部
來源範本的唯讀預覽。請在 Cloud 中開啟,以探索節點並進行變更。
Loading the graph
Open full-size workflow preview- 輸出
- 圖片
- 作者
- ComfyUI
從您的程式碼呼叫此模型
以下請求使用與 Playground 相同的已準備節點圖和設定。每次提交都可能啟動付費執行;若提交結果不明,請勿自動重試提交。
What you need
- Runs on
- Comfy Cloud
- 金鑰
- COMFY_API_KEY
- 您的檔案
- 由程式碼透過其 URL 上傳
需要付費 Cloud 方案與點數。
# Python 3.10+: pip install comfy-sdk==0.4.0
import os
from comfy_sdk import Comfy
api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
"54": {
"class_type": "SaveImageAdvanced",
"inputs": {
"filename_prefix": "ComfyUI",
"format": "png",
"format.bit_depth": "8-bit",
"format.input_color_space": "sRGB",
"images": [
"50:27",
0
]
},
"_meta": {
"title": "Save Image (Advanced)"
}
},
"55": {
"class_type": "SaveImageAdvanced",
"inputs": {
"filename_prefix": "ComfyUI",
"format": "exr",
"format.bit_depth": "16-bit float",
"format.input_color_space": "linear ACEScg",
"images": [
"57",
0
]
},
"_meta": {
"title": "Save Image (Advanced)"
}
},
"56": {
"class_type": "RTXTrueHDR",
"inputs": {
"contrast": 100,
"debanding": True,
"images": [
"50:27",
0
],
"luminance": 650,
"middle_gray": 50,
"output_colorspace": "HDR",
"saturation": 100
},
"_meta": {
"title": "RTX TrueHDR"
}
},
"57": {
"class_type": "ImageColorSpace",
"inputs": {
"destination": "linear ACEScg",
"image": [
"56",
0
],
"source": "HDR"
},
"_meta": {
"title": "Convert Image Color Space"
}
},
"508": {
"class_type": "LoadImage",
"inputs": {
"image": "UPLOADED_image1_FILENAME"
},
"_meta": {
"title": "Load Image"
}
},
"509": {
"class_type": "StringConcatenate",
"inputs": {
"delimiter": "",
"string_a": "Transform this set of images into an equirectangular 360 panorama. Scene:",
"string_b": [
"510",
0
]
},
"_meta": {
"title": "Concatenate Text"
}
},
"510": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "A photograph of the interior of an abandoned brick building. The concrete floor is buried under drifts of sand and dirt littered with splintered wooden planks, curled debris and scattered bricks, and soft overcast daylight spills in through rows of grimy windows and open bays where green foliage presses in from outside. Shot on a DSLR."
},
"_meta": {
"title": "Input Text (Prompt)"
}
},
"507:451": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "qwen_image_2.1_int8_convrot.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"507:453": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_8b_int8_convrot.safetensors",
"device": "default",
"type": "qwen_image"
},
"_meta": {
"title": "Load CLIP"
}
},
"507:454": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "qwen_image_2.1_vae_bf16.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"507:456": {
"class_type": "EmptyLatentImage",
"inputs": {
"batch_size": 1,
"height": 1024,
"width": 2048
},
"_meta": {
"title": "Empty Latent Image"
}
},
"507:457": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"507:458",
0
],
"vae": [
"507:454",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"507:458": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"507:468",
0
],
"model": [
"507:469",
0
],
"negative": [
"507:474",
1
],
"positive": [
"507:474",
0
],
"sampler_name": "euler",
"scheduler": "simple",
"seed": 42,
"steps": 25
},
"_meta": {
"title": "KSampler"
}
},
"507:468": {
"class_type": "ComfySwitchNode",
"inputs": {
"on_false": [
"507:474",
2
],
"on_true": [
"507:456",
0
],
"switch": True
},
"_meta": {
"title": "If/Else Switch"
}
},
"507:469": {
"class_type": "QwenImage21Cache",
"inputs": {
"device": "auto",
"dtype": "default",
"model": [
"507:503",
0
]
},
"_meta": {
"title": "Qwen Image 2.1 Cache"
}
},
"507:474": {
"class_type": "TextEncodeQwenImage21",
"inputs": {
"clip": [
"507:453",
0
],
"images.image_1": [
"508",
0
],
"negative_prompt": "",
"prompt": [
"509",
0
],
"resolution": 0,
"vae": [
"507:454",
0
]
},
"_meta": {
"title": "Text Encode Qwen Image 2.1"
}
},
"507:503": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "Gogodr__qwen-image-21-edit-pano360-lora__pano360_qwen21_edit_v1.safetensors",
"model": [
"507:451",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
},
"50:21": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"507:457",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"50:22": {
"class_type": "SeedVR2LoadVAEModel",
"inputs": {
"cache_model": False,
"decode_tile_overlap": 128,
"decode_tile_size": 1024,
"decode_tiled": True,
"device": "cuda:0",
"encode_tile_overlap": 128,
"encode_tile_size": 1024,
"encode_tiled": True,
"model": "ema_vae_fp16.safetensors",
"offload_device": "none",
"tile_debug": "false"
},
"_meta": {
"title": "SeedVR2 (Down)Load VAE Model"
}
},
"50:25": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"50:43",
0
],
"b": [
"50:30",
0
],
"value": "a*b"
},
"_meta": {
"title": "Upscale to Shortest Edge (pixels)"
}
},
"50:27": {
"class_type": "SeedVR2VideoUpscaler",
"inputs": {
"batch_size": 1,
"color_correction": "lab",
"dit": [
"50:28",
0
],
"enable_debug": False,
"image": [
"507:457",
0
],
"input_noise_scale": 0,
"latent_noise_scale": 0,
"max_resolution": 0,
"offload_device": "cpu",
"prepend_frames": 0,
"resolution": [
"50:25",
0
],
"seed": 1,
"temporal_overlap": 0,
"uniform_batch_size": False,
"vae": [
"50:22",
0
]
},
"_meta": {
"title": "SeedVR2 Video Upscaler (v2.5.24)"
}
},
"50:28": {
"class_type": "SeedVR2LoadDiTModel",
"inputs": {
"attention_mode": "sdpa",
"blocks_to_swap": 0,
"cache_model": False,
"device": "cuda:0",
"model": "seedvr2_ema_3b_fp16.safetensors",
"offload_device": "cpu",
"swap_io_components": False
},
"_meta": {
"title": "SeedVR2 (Down)Load DiT Model"
}
},
"50:30": {
"class_type": "PrimitiveFloat",
"inputs": {
"value": 2
},
"_meta": {
"title": "Upscale Factor"
}
},
"50:40": {
"class_type": "ImpactCompare",
"inputs": {
"a": [
"50:21",
0
],
"b": [
"50:21",
1
],
"cmp": "a <= b"
},
"_meta": {
"title": "ImpactCompare"
}
},
"50:43": {
"class_type": "LayerUtility: If ",
"inputs": {
"if_condition": [
"50:40",
0
],
"when_FALSE": [
"50:21",
1
],
"when_TRUE": [
"50:21",
0
]
},
"_meta": {
"title": "IfElse"
}
}
})
workflow.set_input("508", "image", client.assets.from_url("https://comfy.org/catalog-media/8312b488-282d-4ee8-9905-a16fb4214132/2a126bb1-ccfe-4fda-be7f-469194ab4188"))
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)
for output in job.get_outputs("54"):
output.to_file(output.name)試試範例
關於此工作流程
Equirectangular HDR Skybox Generator 工作流程用於建立高動態範圍(HDR)的等距長方投影圖片,適合用作天空盒,或用於遊戲環境的 look development。此工作流程利用 Qwen-Image 與 SeedVR2 等進階 AI 模型,以及 comfyui_essentials、seedvr2_videoupscaler 等自訂節點,產生高品質、寫實的材質。流程從 CLIPTextEncode 節點開始,解讀輸入提示詞以引導圖片生成。接著使用 ModelSamplingAuraFlow 節點對影像資料進行取樣,再由 KSampler 與 UNETLoader 節點進一步精煉。VAELoader 與 VAEDecode 節點在影像資料的編碼與解碼中扮演關鍵角色,確保最終輸出同時具備高解析度以及視覺準確性。最後,工作流程包含 SaveImage 與 StringConcatenate 等節點,用於管理輸出與檔案命名,以便整合到遊戲開發管線中。
問答
等距長方形影像是一種全景影像格式,用來表達 360 度視野,常用於 VR 與遊戲開發中建立沉浸式環境。
Qwen-Image 模型會根據提示詞生成高品質且細節豐富的影像,確保最終天空盒的視覺呈現與提示內容一致。
可以。雖然它針對遊戲開發做了最佳化,但凡是需要高品質等距長方形 HDR 影像的情境都能使用,例如 VR 體驗或建築視覺化。
此工作流程設計為將最終影像放大至 4K 解析度,提供適用於現代遊戲引擎的細節與畫質。
相關工作流程
- Qwen, Qwen-Image
Qwen Image 2512
- Qwen-Image
Qwen Image Edit 2509
- Qwen-Image
Qwen Image:插畫LoRA
- Qwen-Image
Qwen Image:軟糖動物LoRA
- Qwen-Image
Qwen-Image ControlNet 模型補丁
- Qwen-Image
Qwen-Image InstantX ControlNet
- Qwen-Image
Qwen-Image Union Control
- Qwen-Image
Qwen千問-圖像:文生圖
- Qwen-Image
Qwen千問-圖像:文生圖
- Qwen-Image
Qwen千問圖像局部重繪ControlNet