Chroma1 Radiance Text to Image
Chroma1-Radiance works directly with image pixels instead of compressed latents, delivering higher quality images with reduced artifacts and distortion.
概要
The 'Chroma1 Radiance Text to Image' workflow is designed to enhance image generation by working directly with image pixels rather than relying on compressed latents. This approach significantly improves the quality of generated images, reducing artifacts and distortion commonly associated with latent-based methods.
The workflow utilizes the Chroma model, known for its ability to handle high-resolution image data effectively. By employing nodes such as SaveImage and MarkdownNote, users can seamlessly generate and save high-quality images while integrating informative notes within their workflow. The unique node '107cc5d5-a32e-4420-96ef-83996f29ac4c' plays a crucial role in processing and refining the image outputs, ensuring that the final results meet high standards of visual fidelity.
入力するもの
- ワークフローを読み込み中
ComfyUI で実行できます。 このワークフローはこのページでは実行できません。すべてが読み込まれた状態でComfy Cloudで開くか、ご自身のComfyUI用にダウンロードしてください。
Cloudで試すワークフローの内部
ノードグラフの読み取り専用プレビューです。ノードを編集するには、Comfy Cloudで開くかダウンロードしてください。
Loading the graph
Open full-size workflow preview- 作成者
- ComfyUI
カスタムノードが必要です
- ワークフローを読み込み中
コードからこのワークフローを使用する
可能な場合はワークフローグラフと入力から生成されます。それ以外の場合は保存された例が表示されます。料金が発生する場合があるため、コードを実行する前に認証情報とエンドポイントを確認してください。
What you need
- Runs on
- Comfy Cloud
- キー
- COMFY_API_KEY
有料の Cloud プランとクレジットが必要です。
# 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({
"740": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "Chroma-Radiance",
"images": [
"762:298",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"762:298": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"762:753",
0
],
"vae": [
"762:710",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"762:693": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"762:741",
0
],
"text": "Hyperrealistic macro photograph of a team of tiny bakers—each precisely 2 inches tall—collaborating on an enormous, golden-brown croissant with flaky, layered textures. The bakers are engaged in dynamic, detailed actions: one uses a miniature wooden bucket to spread rich, creamy butter between the croissant’s layers, another climbs a thin rope ladder to evenly pipe smooth, glossy chocolate filling onto the top, and a third brushes a light egg wash with a tiny pastry brush. The scene is bathed in warm, soft kitchen lighting with cinematic depth—subtle highlights on the croissant’s golden crust, gentle shadows that emphasize texture, and a soft glow from overhead pendant lights. Floating flour dust particles catch the light, adding a sense of movement and realism, while tiny details like the bakers’ stitched cloth aprons, smudged flour on their faces, the rough wood of the worktable, and the slight sheen of melted butter on the croissant are rendered with ultra-precision. Ultra-detailed, 8K resolution, photorealistic textures, sharp focus on the bakers and croissant, shallow depth of field to blur the background slightly, rich warm color palette, lifelike proportions, and a cozy, whimsical atmosphere that balances realism with charm."
},
"_meta": {
"title": "Positive"
}
},
"762:694": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 3.5,
"model": [
"762:701",
0
],
"negative": [
"762:728",
0
],
"positive": [
"762:693",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"762:700": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"762:701": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": [
"762:747",
0
],
"sampling": "flow",
"shift": 1
},
"_meta": {
"title": "Flow Shift"
}
},
"762:710": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "pixel_space"
},
"_meta": {
"title": "Load VAE"
}
},
"762:718": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 918944845349229
},
"_meta": {
"title": "SEED"
}
},
"762:728": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"762:741",
0
],
"text": "This low quality greyscale unfinished sketch is inaccurate and flawed. The image is very blurred and lacks detail with excessive chromatic aberrations and artifacts. The image is overly saturated with excessive bloom."
},
"_meta": {
"title": "Negative"
}
},
"762:731": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "chroma-radiance-x0.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"762:733": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "t5xxl_fp8_e4m3fn_scaled.safetensors",
"device": "default",
"type": "chroma"
},
"_meta": {
"title": "Load CLIP"
}
},
"762:741": {
"class_type": "T5TokenizerOptions",
"inputs": {
"clip": [
"762:733",
0
],
"min_length": 0,
"min_padding": 0
},
"_meta": {
"title": "T5 Tokenizer Options"
}
},
"762:747": {
"class_type": "ChromaRadianceOptions",
"inputs": {
"end_sigma": 0,
"force_sequential_txt_ids": False,
"model": [
"762:731",
0
],
"nerf_tile_size": -1,
"preserve_wrapper": True,
"start_sigma": 1
},
"_meta": {
"title": "ChromaRadianceOptions"
}
},
"762:751": {
"class_type": "BetaSamplingScheduler",
"inputs": {
"alpha": 0.4,
"beta": 0.4,
"model": [
"762:701",
0
],
"steps": 30
},
"_meta": {
"title": "BetaSamplingScheduler"
}
},
"762:753": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"762:694",
0
],
"latent_image": [
"762:760",
0
],
"noise": [
"762:718",
0
],
"sampler": [
"762:700",
0
],
"sigmas": [
"762:751",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"762:760": {
"class_type": "EmptyChromaRadianceLatentImage",
"inputs": {
"batch_size": 1,
"height": 1024,
"width": 1024
},
"_meta": {
"title": "EmptyChromaRadianceLatentImage"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)よくある質問
This workflow operates directly on image pixels, resulting in higher quality images with fewer artifacts compared to those generated from compressed latents.
This node is essential for processing and refining the image outputs, ensuring that the final images are of high visual fidelity.
Ensure that you have the latest version of ComfyUI and the necessary models installed. Craft detailed text prompts to guide the image generation process effectively.
Yes, the high-quality images generated can be used for various commercial applications, such as marketing, advertising, and product visualization.