参数说明
必需参数
| 参数 | 类型 | 默认值 | 说明 |
|---|---|---|---|
| prompt | 字符串 | "" | 您希望在输出图像中看到的内容。强有力、描述性的提示词，清晰定义元素、颜色和主题将带来更好的结果 |
| model | 选择项 | - | 选择使用的Stability SD 3.5模型 |
| aspect_ratio | 选择项 | ”1:1” | 生成图像的宽高比 |
| style_preset | 选择项 | ”None” | 可选的期望图像风格预设 |
| cfg_scale | 浮点数 | 4.0 | 扩散过程对提示文本的遵循程度（更高的值使图像更接近您的提示词）。范围：1.0 - 10.0，步长：0.1 |
| seed | 整数 | 0 | 用于创建噪声的随机种子，范围0-4294967294 |
可选参数
| 参数 | 类型 | 默认值 | 说明 |
|---|---|---|---|
| image | 图像 | - | 输入图像。当提供图像时，节点将切换到图像到图像模式 |
| negative_prompt | 字符串 | "" | 您不希望在输出图像中看到的关键词。这是一个高级功能 |
| image_denoise | 浮点数 | 0.5 | 输入图像的去噪程度。0.0产生与输入完全相同的图像，1.0则相当于没有提供任何图像。范围：0.0 - 1.0，步长：0.01。仅在提供输入图像时有效 |
输出
| 输出 | 类型 | 说明 |
|---|---|---|
| IMAGE | 图像 | 生成的图像 |
使用示例
Stability AI Stable Diffusion 3.5 Image 工作流示例
Stability AI Stable Diffusion 3.5 Image 工作流示例
注意事项
- 当提供输入图像时，节点将从文本到图像模式切换到图像到图像模式
- 在图像到图像模式下，宽高比参数将被忽略
- 模式选择会根据是否提供图像自动切换：
- 未提供图像：文本到图像模式
- 提供图像：图像到图像模式
- 如果style_preset设置为”None”，则不会应用任何预设风格
源码
[节点源码 (更新于2025-05-07)]class StabilityStableImageSD_3_5Node:
"""
Generates images synchronously based on prompt and resolution.
"""
RETURN_TYPES = (IO.IMAGE,)
DESCRIPTION = cleandoc(__doc__ or "") # Handle potential None value
FUNCTION = "api_call"
API_NODE = True
CATEGORY = "api node/image/Stability AI"
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"prompt": (
IO.STRING,
{
"multiline": True,
"default": "",
"tooltip": "What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results."
},
),
"model": ([x.value for x in Stability_SD3_5_Model],),
"aspect_ratio": ([x.value for x in StabilityAspectRatio],
{
"default": StabilityAspectRatio.ratio_1_1,
"tooltip": "Aspect ratio of generated image.",
},
),
"style_preset": (get_stability_style_presets(),
{
"tooltip": "Optional desired style of generated image.",
},
),
"cfg_scale": (
IO.FLOAT,
{
"default": 4.0,
"min": 1.0,
"max": 10.0,
"step": 0.1,
"tooltip": "How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt)",
},
),
"seed": (
IO.INT,
{
"default": 0,
"min": 0,
"max": 4294967294,
"control_after_generate": True,
"tooltip": "The random seed used for creating the noise.",
},
),
},
"optional": {
"image": (IO.IMAGE,),
"negative_prompt": (
IO.STRING,
{
"default": "",
"forceInput": True,
"tooltip": "Keywords of what you do not wish to see in the output image. This is an advanced feature."
},
),
"image_denoise": (
IO.FLOAT,
{
"default": 0.5,
"min": 0.0,
"max": 1.0,
"step": 0.01,
"tooltip": "Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.",
},
),
},
"hidden": {
"auth_token": "AUTH_TOKEN_COMFY_ORG",
},
}
def api_call(self, model: str, prompt: str, aspect_ratio: str, style_preset: str, seed: int, cfg_scale: float,
negative_prompt: str=None, image: torch.Tensor = None, image_denoise: float=None,
auth_token=None):
validate_string(prompt, strip_whitespace=False)
# prepare image binary if image present
image_binary = None
mode = Stability_SD3_5_GenerationMode.text_to_image
if image is not None:
image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read()
mode = Stability_SD3_5_GenerationMode.image_to_image
aspect_ratio = None
else:
image_denoise = None
if not negative_prompt:
negative_prompt = None
if style_preset == "None":
style_preset = None
files = {
"image": image_binary
}
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/stable-image/generate/sd3",
method=HttpMethod.POST,
request_model=StabilityStable3_5Request,
response_model=StabilityStableUltraResponse,
),
request=StabilityStable3_5Request(
prompt=prompt,
negative_prompt=negative_prompt,
aspect_ratio=aspect_ratio,
seed=seed,
strength=image_denoise,
style_preset=style_preset,
cfg_scale=cfg_scale,
model=model,
mode=mode,
),
files=files,
content_type="multipart/form-data",
auth_token=auth_token,
)
response_api = operation.execute()
if response_api.finish_reason != "SUCCESS":
raise Exception(f"Stable Diffusion 3.5 Image generation failed: {response_api.finish_reason}.")
image_data = base64.b64decode(response_api.image)
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
return (returned_image,)