Tasks and inputs
krea/Krea-2-Raw is listed for Text-to-image. It accepts text and produces image. Use the publisher’s input format and preprocessing for your chosen deployment.
Krea 2 Raw: a base checkpoint for further training, not the recommended everyday inference release.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Krea 2 Raw is a Krea text-to-image checkpoint in the Krea 2 family.
Raw is the base checkpoint before the additional post-training and distillation used for Turbo. The publisher does not recommend Raw for ordinary inference; it is a starting point for fine-tuning or further training.
For ordinary image generation, use a prompt set with recognizable objects, composition constraints, text and difficult spatial relationships. Keep resolution and other generation settings recorded. For training, judge the resulting adapted model on held-out prompts rather than score only the starting checkpoint.
Weights are gated under the Krea 2 Community License. Open-weight access should not be described as an unrestricted Apache-style release. Review the license and the project's documented access requirements for your intended use.
Check that your runtime supports the Krea2 pipeline and selected checkpoint. Record the checkpoint, adapters, precision, resolution, steps and generation time with every comparison. Runtime and image size affect memory needs; this profile does not invent a universal GPU requirement.
Explore text-to-image models or compare Raw and Turbo.
Compare the model on the work you need to complete.
krea/Krea-2-Raw is listed for Text-to-image. It accepts text and produces image. Use the publisher’s input format and preprocessing for your chosen deployment.
Choose the output size and quality your design needs. Include drafts and revisions when budgeting an accepted image.
The weights are downloadable under Krea 2 Community License. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Alibaba
Qwen-Image-2.1-Turbo creates and edits images, including reference-guided and transparency workflows; hosted billing is separate from local deployment.
Alibaba
Qwen-Image-2.1-Pro creates and edits images, including reference-guided and transparency workflows; hosted billing is separate from local deployment.
Meta
Muse Image 1.0 generates and edits images through conversational or single-shot endpoints, with flat per-image Meta Model API billing.
krea
Krea 2 Turbo: the post-trained and distilled Krea 2 checkpoint for image generation.
OpenAI
GPT-5.4 Image 2 from OpenAI: Image model for prompt-driven generation, editing, and visual design workflows.
Qwen
Qwen/Qwen-Image is a source-linked Hugging Face repository assigned to Text-to-image. Its recorded task interface accepts text and produces image.