Ideogram4 Fal
ideogram-4-non-commercial
Model source
- Kind
- Other
- File size
- 5.26–17.3 GB
- Base model
- fal/ideogram-v4-fast
- Version
- vRevision 9fcb42c
- Updated
- Oct 2, 2026
- Downloads
- 4.7K
- Source
- Hugging Face
Source description
Repackages of Fal's Ideogram4-Fast and Ideogram4-Instant to ComfyUI compatible files, with int8 and nvfp4 conversion done with Silveroxides/convert_to_quant, targeting only attention and MLP tensors.
Officially recommended parameters:
- for Fast: 20 steps, CFG 1
- for Instant: 8 steps, CFG 1
Reported gen speed on a 5090 at 1536x1536:
- bf16: 0.85 it/s
- int8: 1.7 it/s
- nvfp4: 1.9 it/s
Note that Fast has QAD (Quantization Aware Distillation) so nvfp4 can be better than its larger variants, especially on long texts. Fal's readme of Instant says it doesn't have QAD but nvfp4 is just as good as the larger ones too.
Sources
1 source
Sources
1 sourceVerified Oct 2
Model artifacts
6 artifacts
Model artifacts
6 artifactsIdeogram4-fast_bf16.safetensors
safetensors · 17.3 GB · SHA-256 436c6de3dbf0…77b8 · Hugging Face
DownloadIdeogram4-fast_int8-convrot-simple.safetensors
safetensors · 8.92 GB · SHA-256 50462e454680…306f · Hugging Face
DownloadIdeogram4-fast_nvfp4-simple.safetensors
safetensors · 5.26 GB · SHA-256 6ab058018954…eda8 · Hugging Face
DownloadIdeogram4-instant_bf16.safetensors
safetensors · 17.3 GB · SHA-256 037ecbc66173…a3c0 · Hugging Face
DownloadIdeogram4-instant_int8-convrot-simple.safetensors
safetensors · 8.92 GB · SHA-256 bdac20199a99…76cd · Hugging Face
DownloadIdeogram4-instant_nvfp4-simple.safetensors
safetensors · 5.26 GB · SHA-256 f127b9b345b4…63e5 · Hugging Face
DownloadSource excerpts
3 excerpts
Source excerpts
3 excerpts--- license: other license_name: ideogram-4-non-commercial license_link: https://huggingface.co/ideogram-ai/ideogram-4-fp8/blob/main/LICENSE.md base_model_relation: quantized library_name: diffusers tags: - comfyui - safetensors base_model: - fal/ideogram-v4-fast - fal/ideogram-v4-instant --- Repackages of Fal's [Ideogram4-Fast](https://huggingface.co/fal/ideogram-v4-fast) and [Ideogram4-Instant](https://huggingface.co/fal/ideogram-v4-instant) to ComfyUI compatible files, with int8 and nvfp4 conversion done with [Silveroxides/convert_to_quant](https://github.com/silveroxides/convert_to_quant), targeting only attention and MLP tensors. Officially recommended parameters: - for Fast: 20 steps, CFG 1 - for Instant: 8 steps, CFG 1 Reported gen speed on a 5090 at 1536x1536: - bf16: 0.85 it/s - int8: 1.7 it/s - nvfp4: 1.9 it/s Note that Fast has QAD (Quantization Aware Distillation) so nvfp4 can be better than its larger variants, especially on long texts. Fal's readme of Instant says it doesn't have QAD but nvfp4 is just as good as the larger ones too.
--- license: other license_name: ideogram-4-non-commercial license_link: https://huggingface.co/ideogram-ai/ideogram-4-fp8/blob/main/LICENSE.md --- Repackages of Fal's [Ideogram4-Fast](https://huggingface.co/fal/ideogram-v4-fast) and [Ideogram4-Instant](https://huggingface.co/fal/ideogram-v4-instant) to ComfyUI compatible files, with int8 and nvfp4 conversion done with [Silveroxides/convert_to_quant](https://github.com/silveroxides/convert_to_quant), targeting only attention and MLP tensors. Officially recommended parameters: - for Fast: 20 steps, CFG 1 - for Instant: 8 steps, CFG 1 Reported gen speed on a 5090 at 1536x1536: - bf16: 0.85 it/s - int8: 1.7 it/s - nvfp4: 1.9 it/s Note that Fast has QAD (Quantization Aware Distillation) so nvfp4 can be better than its larger variants, especially on long texts. Fal's readme of Instant says it doesn't have QAD but nvfp4 is just as good as the larger ones too.
--- license: other license_name: ideogram-4-non-commercial license_link: https://huggingface.co/ideogram-ai/ideogram-4-fp8/blob/main/LICENSE.md ---
