UPDATE COMFYUI TO THE LATEST UPDATE!
Ideogram 4 is Ideogram's first open weight text-to-image model. It is a state-of-the-art foundation model trained from scratch — not a fine-tune of any existing model. It introduces a new structured JSON prompting interface, with best-in-class multilingual text rendering, deep language understanding, explicit bounding-box layout and color-palette controls, and native 2k resolution images. The easiest way to try the model is online at ideogram.ai.
Diffusion Model (nvfp4) - REQUIRED!
Unconditional Diffusion Model (nvfp4) - REQUIRED!
https://huggingface.co/Comfy-Org/Ideogram-4/blob/main/diffusion_models/ideogram4_unconditional_nvfp4_mixed.safetensors
Text Encoder (fp8)
https://huggingface.co/black-forest-labs/FLUX.2-small-decoder/blob/main/full_encoder_small_decoder.safetensors
requires both diffusion models. youll understand why when you see the workflow deconstructed. ive set this workflow up as i dont like the subgraph workflows. takes away from the joy of comfy imo <3
Description
gguf coming shortly
FAQ
Comments (1)
I'm using the workflows provided on comfy site since yesterday, had to add a clean ram node to prevent "buffer exhausted" error or something like that. But my images are atrocious. Crossed eyes, deformed hands, etc. No idea how people are getting such good results. I'll try this one and come back later to say how it goes 🤣
Edit: still looks like dog crap https://civitai.red/posts/29012297