Ideogram 4 image generator
Generate images from scene prompts using the fixed Ideogram 4 conditional and unconditional model pair. Enter your completed scene description in Positive prompt; structured JSON is recommended for compositions containing text and positioned objects. No uploaded media is required.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 23, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Positive prompt
CLIPTextEncode
Output size
ResolutionSelector
Sampling preset
CustomCombo
Extended
Additional surfaced controls
Guidance
DualModelGuider
Guidance override
CFGOverride
Randomization
RandomNoise
Sampling
KSamplerSelect
Image count
EmptyFlux2LatentImage
What you need
Hardware and download-size estimates are not available yet.
Output
- Sweet Tea Preview Image · image
Requirements
Models
4- File unverified
VAE · Hugging Face · Comfy-Org/flux2-dev
ideogram4_int8_convrot.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/Ideogram-4 · Ideogram 4
ideogram4_unconditional_int8_convrot.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/Ideogram-4 · Ideogram 4
qwen3vl_8b_fp8_scaled.safetensors
File unverifiedText encoder · Hugging Face · Comfy-Org/Qwen3-VL · Qwen3 VL
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source