Text to Image
Text-to-image pipelines built on Ideogram 4 and Krea 2 GGUF quants.
Models and formats
The following models support Text-to-Image modalities: krea2-gguf.json
| Model | Strength | Tradeoff |
|---|---|---|
| Ideogram 4 | Excellent prompt following, great text rendering | Strict JSON prompt structure is cumbersome to follow. |
| Krea 2 | Highly creative, decent prompt following | Text rendering not always perfect |
Loading instructions
- Download the required GGUF files from Hugging Face and put it in the
models/diffusion_modelsComfyUI directory. You only need one quant format, not all. - Replace the default diffusion model node with the GGUF loader.
- Point the loader at the model's .gguf file.
- Load the pruned text encoder GGUF alongside it.
- Set the sampler steps and CFG to the model's recommended values. (Using a GGUF instead of a safetensors/other file format does not affect what sampling/scheduling/etc settings you need to set.)