Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →artokun/ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows — local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control
Passed 22 of 22 test cases with the skill, and 3 of 22 without it.
and 29 more in the full report
20 fixed3 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
In the modular sampler stack for Ideogram 4 (`BasicScheduler` and `KSamplerSelect`), which sampler algorithm and scheduler mode are configured by default?
| Checked | Without skill | With skill |
|---|---|---|
| specifies euler for KSamplerSelect | Passed | Passed |
| specifies simple scheduler for BasicScheduler | Missed | Passed |
The instructions your model reads when the skill loads.
This is a LOCAL open-weights pipeline, NOT the hosted Ideogram API. There is no API key, no IdeogramGenerate API node, and no network call at generation time. Comfy-Org released the Ideogram 4 weights on Hugging Face and they run entirely on your GPU via standard UNETLoader / CLIPLoader / VAELoader nodes. (Note: ComfyUI also ships separate API/"partner" nodes that call the paid hosted Ideogram service. That is a different thing and is not what this workflow uses.)
Ideogram 4 is best known for text rendering / typography, poster and graphic-design layouts, and prompt adherence. The hallmark of this workflow is a structured JSON prompt (a "compositional deconstruction" caption with bounding boxes) instead of a plain text prompt. This is what gives precise control over where text and objects land in the frame.
Source workflow this skill is derived from: IDEOGRAM_ULTRA_WORKFLOW-V2.json (UI format, 66 nodes, 4 subgraphs), by Aitrepreneur. It provides both a TEXT TO IMAGE path and an IMAGE TO IMAGE path.
ideogram4_fp8_scaled) and an ..._unconditional_fp8_scaled model. A DualModelGuider node uses both to perform asymmetric classifier-free guidance; the unconditional model provides the CFG baseline. There is no negative text prompt; negative conditioning is ConditioningZeroOut.qwen3vl_8b_fp8_scaled is the actual diffusion text encoder (loaded with CLIPLoader, type ideogram4).gemma4_e4b_it_fp8_scaled is used only inside an optional prompt-builder subgraph (a TextGenerate node) that auto-writes the structured JSON from a plain idea. It is not the diffusion encoder.The workflow needs these four custom node packs (clone into ComfyUI/custom_nodes/). Exact repos from the installer scripts:
git clone https://github.com/ltdrdata/ComfyUI-Manager.git
git clone https://github.com/rgthree/rgthree-comfy
git clone https://github.com/kijai/ComfyUI-KJNodes
git clone https://github.com/cubiq/ComfyUI_essentials
Ideogram4PromptBuilderKJ, ImageSharpenKJ, TextGenerate, and the Ideogram 4 helper nodes. Required.Power Lora Loader, Fast Groups Muter/Bypasser, Label, Any Switch. (Used for UI/convenience; the core pipeline still works without them.)ImageResize+ (used in the img2img path).The core nodes used in the simplified workflows below (
UNETLoader,CLIPLoader,VAELoader,DualModelGuider,SamplerCustomAdvanced,ModelSamplingAuraFlow,BasicScheduler,EmptyFlux2LatentImage,CLIPTextEncode,ConditioningZeroOut,VAEDecode) are built into ComfyUI (recent versions). OnlyIdeogram4PromptBuilderKJ/ImageSharpenKJrequire KJNodes.
Five files. Folder layout and download URLs are taken verbatim from IDEOGRAM_ULTRA-MODELS-NODES_INSTALL.bat / ...RUNPOD.sh:
test cases passed, vs 3 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.