语言

Flux 3 text-to-image workflow

从 ModelTrends 导入

A basic Flux 3 text-to-image workflow: the Klein base in BF16 with a 9GB Text Upscaler, the Flux 2 VAE and a Qwen VL text encoder. 50 steps is recommended. On Graydient you can also run Distill, Base, BF16 Text Encoder and Upscaler presets for this family, the same ones listed on ModelTrends. A typical render takes about three minutes and wants around 28 GB of VRAM.

兼容 / 可用于 Graydient 支持的应用

选项

选项映射到默认
(prompt positive)Text (Multiline) → value—
/guidanceKSampler → cfg3.5
/imagesEmpty Flux 2 Latent → batch_size1
/seedKSampler → seedrandom
/sizeEmpty Flux 2 Latent → width, height1024 × 1024
/stepsKSampler → steps50

使用的模型

Flux 3 (v11) 模型由 ModelTrends 通过短代码 /run:flux3 导入 在 ModelTrends 查看

面向开发者(可选)

示例 API 代码片段。你可以用这个工作流程构建自己的应用程序供个人使用。准备好向全球部署时,请联系我们获取高可用服务器。查看完整渲染 API 文档。

curl https://cloud.graydient.ai/api/v3/render/ \
  -X POST \
  -H "Content-Type: application/vnd.api+json" \
  -H "Accept: application/vnd.api+json" \
  -H "Authorization: Bearer $GRAYDIENT_TOKEN" \
  -d '{
    "prompt": "/workflow /run:flux3 a lighthouse on a cliff at dusk",
    "callback_url": "https://example.com/webhook/render"
  }'

这就是幕后工作原理。已经为你配置好了。上表中的参数插入这些槽位,允许你更改工作方式和加载的模型。你无需理解或修改它——它已经设置好,能直接使用。

Load Diffusion Model MODEL to KSampler; Load CLIP CLIP to CLIP Text Encode (Prompt); Load CLIP (9GB Text Upscaler) CLIP to CLIP Text Encode (Prompt); Text (Multiline) STRING to CLIP Text Encode (Prompt); CLIP Text Encode (Prompt) CONDITIONING to KSampler; Empty Flux 2 Latent LATENT to KSampler; KSampler LATENT to VAE Decode; Load VAE VAE to VAE Decode; VAE Decode IMAGE to Save Image
Load Diffusion Model#28
MODEL
unet_nameflux3_image_klein_bas…
Load CLIP (9GB Text Upscaler)#25
CLIP
clip_nameqwen3.5_9b_flux3_prom…
Load CLIP#30
CLIP
clip_nameqwen3vl_4b_bf16
Load VAE#32
VAE
vae_nameflux2-vae
Text (Multiline)#24
STRING
valuea lighthouse on a cli…(prompt)
CLIP Text Encode (Prompt)#6
clipCONDITIONING
clip_upscale
text
Empty Flux 2 Latent#35
LATENT
width1024/size
height1024/size
batch_size1/images
KSampler#31
modelLATENT
positive
latent_image
seedrandom/seed
steps50/steps
cfg3.5/guidance
VAE Decode#8
samplesIMAGE
vae
Save Image#9
images
filename_prefixGraydient

只读视图。高亮的标签是调用时可设置的选项。 Base BF16 with 9GB Text Upscaler; 50 steps recommended.

所有工作流:强大工作流程

查看套餐和价格