Watch the full video first if you want to understand how this Ideogram 4 reference latent reconstruction workflow works in practice. The video shows how a reference image can be analyzed, converted into a structured Ideogram 4 JSON prompt, encoded into latent space, and then regenerated through a controlled image-to-image reconstruction pipeline.
This ComfyUI workflow is designed for Ideogram 4 image-to-image reference latent reconstruction. Its main purpose is to rebuild an existing image by combining two control routes: a visual-language JSON prompt route and a reference latent remix route. Compared with a pure text-to-image workflow, this graph gives Ideogram 4 both a structured description of the image and a latent-space reference starting point. Compared with ordinary image-to-image workflows, it is more experimental and more design-oriented, because the final stability comes from both the reference latent and the reconstructed JSON prompt.
The workflow starts from a reference image. The image is scaled and prepared through the image scaling section, then encoded into latent space through VAEEncode. This encoded latent is sent into the sampler as the starting latent instead of using a blank EmptyFlux2LatentImage canvas. The older text-to-image empty latent path is intentionally disconnected in this version, because the workflow is focused on reference reconstruction rather than pure generation.
A key technical point is the SplitSigmasDenoise stage. The scheduler output is split before entering the sampler, allowing the workflow to run a controlled denoise range over the reference latent. This makes the result behave like a forced latent remix route: it may preserve part of the reference image’s composition and structure, while still allowing Ideogram 4 to reinterpret the image according to the prompt and denoise strength. It is not a classic SD 1.5-style img2img pipeline, so the result can drift depending on denoise settings, prompt strength, and reference complexity.
The second major control route is the Vision LLM prompt reconstruction chain. The workflow uses a reference image together with target width and height information, then asks the RH visual completion section to generate an Ideogram 4-compatible structured JSON prompt. This JSON can describe the subject, background, layout hierarchy, bounding boxes, readable text, color palette, lighting, material, medium, and overall design logic. This is especially useful for posters, thumbnails, graphic layouts, typography-based images, product visuals, and image washing tasks where composition matters.
The generation route uses Ideogram 4 as the main model, with an unconditional branch, DualModelGuider, CFGOverride, Ideogram4Scheduler, SamplerCustomAdvanced, Flux2 VAE decoding, and SaveImage output. The workflow also includes Quality / Default / Turbo presets. Quality uses more steps for final polish, Default is suitable for normal testing, and Turbo is useful for fast previewing.
This workflow is best understood as a hybrid reconstruction tool. The reference latent helps preserve visual structure, while the JSON prompt helps preserve semantic layout, objects, text, and design intent. Together, they make the workflow useful for image remaking, visual reference reconstruction, poster redesign, structured wash-image workflows, cover image rebuilding, typography layout testing, and reusable Ideogram 4 prompt generation.
Main features:
Ideogram 4 image-to-image reconstruction workflow
Reference image latent remix route
Load Image to ImageScale to VAEEncode pipeline
Reference latent injected into SamplerCustomAdvanced
SplitSigmasDenoise denoise control
RH visual completion JSON prompt reconstruction
Image-only prompt compiler logic
Subject, background, bbox, text, color, and layout extraction
Ideogram 4 FP8 main model support
Ideogram unconditional branch
DualModelGuider guidance structure
CFGOverride guidance behavior control
Flux2 VAE decoding
Quality / Default / Turbo preset system
Width and height auto-aligned to valid values
SaveImage final output
Suggested workflow:
Prepare a clean reference image first. The image should have a readable subject, clear composition, and visible layout. Upload it into the workflow, set the target width and height, then let the RH visual completion section generate the structured Ideogram 4 JSON prompt. Check the JSON before rendering. If the result is too different from the reference, lower the denoise range or strengthen the JSON descriptions for layout, subject, color, and typography. If the result stays too close and lacks improvement, increase the reconstruction freedom or simplify the prompt. Use Default mode for the first test, Turbo for quick structure checks, and Quality mode only after the layout direction is stable.
⚙️ RunningHub Workflow
Try the workflow online right now — no installation required.
👉 Workflow: https://www.runninghub.ai/post/2064321322360074241?inviteCode=rh-v1111
If the results meet your expectations, you can later deploy it locally for customization.
🎁 Fan Benefits: Register to get 1000 points + daily login 100 points — enjoy 4090 performance and 48 GB super power!
📺 Bilibili Updates (Mainland China & Asia-Pacific)
If you’re in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown.
📺 Bilibili Video: https://www.bilibili.com/video/BV1RtEQ6SEsS/
☕ Support Me on Ko-fi
If you find my content helpful and want to support future creations, you can buy me a coffee ☕.
Every bit of support helps me keep creating — just like a spark that can ignite a blazing flame.
👉 Ko-fi: https://ko-fi.com/aiksk
💼 Business Contact
For collaboration or inquiries, please contact aiksk95 on WeChat.
⚙️打开下方链接即可在线体验,无需安装。
👉 工作流: https://www.runninghub.ai/post/2064321322360074241?inviteCode=rh-v1111
如果觉得效果理想,你也可以在本地进行自定义部署。
🎁 粉丝福利: 注册即送 1000 积分,每日登录 100 积分,畅玩 4090 体验 48 G 超级性能!
📺 Bilibili 更新(中国大陆及南亚太地区)
如果你在中国大陆或南亚太地区,可以通过下方视频查看该工作流的实测效果与构思讲解。
📺 B站视频: https://www.bilibili.com/video/BV1RtEQ6SEsS/
我会在 夸克网盘 持续更新模型资源:
👉 https://pan.quark.cn/s/20c6f6f8d87b
这些资源主要面向本地用户,方便进行创作与学习。
