Comfy-Org/Ideogram-4
Summary
Ideogram-4 model repackaged for ComfyUI, including fp8 scaled diffusion models, Qwen3VL text encoder, and FLUX VAE.
View Cached Full Text
Cached at: 06/09/26, 08:56 AM
Comfy-Org/Ideogram-4 Β· Hugging Face
Source: https://huggingface.co/Comfy-Org/Ideogram-4
Repackaged model files for ComfyUI.
Original model repository:https://huggingface.co/ideogram-ai/ideogram-4-fp8
Place the files in the following folders:
π ComfyUI/
βββ π models/
β βββ π diffusion_models/
β β βββ ideogram4_fp8_scaled.safetensors
β β βββ ideogram4_unconditional_fp8_scaled.safetensors
β βββ π text_encoders/
β β βββ qwen3vl_8b_fp8_scaled.safetensors
β βββ π vae/
β β βββ flux2-vae.safetensors
Downloads last month-
Downloads are not tracked for this model.
Inference ProvidersNEW
This model isnβt deployed by any Inference Provider.πAsk for provider support
Space usingComfy-Org/Ideogram-41
Similar Articles
ideogram-ai/ideogram-4-nf4
Ideogram has released Ideogram 4, their first open-weight text-to-image model trained from scratch, featuring state-of-the-art multilingual text rendering, JSON-structured prompting, bounding-box layout controls, and native 2K resolution output. The NF4-quantized version is available on Hugging Face, with the model claimed to be the best open-weight image model and competitive with proprietary frontier models.
Ideogram 4.0
Ideogram 4.0 is released as an open-weight model with layout control for generating design-ready images.
Ideogram 4 (GitHub Repo)
Ideogram 4 is an open-weight text-to-image model trained from scratch, featuring structured JSON prompting, best-in-class multilingual text rendering, bounding-box layout controls, color-palette controls, and native 2K resolution output.
Comfy-Org/ERNIE-Image
Comfy-Org has repackaged Baidu's ERNIE-Image and ERNIE-Image-Turbo models for ComfyUI integration, providing ready-to-use model files organized for the ComfyUI node-based image generation framework.
Ideogram 4 is open source! (top ranked on DesignArena)
Ideogram 4, an open-source text-to-image model, is released with state-of-the-art performance, structured JSON prompting, and multilingual text rendering.