<p>Krea 2 Turbo is the open-weights, distilled checkpoint of Krea 2 - Krea AI's first foundation image model, trained from scratch with a focus on how an image feels rather than just what it contains. Turbo is an 8-step build distilled from Krea 2 RAW and optimized for fast, high-quality inference at high resolution.</p>
<p><strong>Originally released by <a href="https://www.krea.ai">Krea AI</a> on Hugging Face.</strong> All credit for the model goes to the Krea team and the contributors listed below. Civitai is hosting a mirror so creators can generate with it on-site - please head to the <a href="https://huggingface.co/krea/krea-2-turbo">original repo</a> for weights, the technical report, and to support the project directly.</p>
<h3>Built by</h3>
<p>Krea AI, with Sangwu Lee, Erwann Millon, Le Zhuo, Matthew Newton, Andrei Filatov, Abhinay Devarinti, Dazhi Zhong, Avram Djordjevic, Gabriel Menezes, Will Beddow, Titus Ebbecke, Mihai Petrescu, Owen Fahey, Gian Saß, Felix Gil, and Victor Perez.</p>
<h3><strong>8-step distilled for speed</strong></h3>
<p>Turbo bakes guidance into the weights, so it runs without classifier-free guidance - Krea's recommended settings are 8 steps at CFG 0.0 with a constant timestep shift (mu) of 1.15. It generates at 1k to 2k resolution and supports outputs up to 2048x2048, making it the build to reach for when you want Krea 2 aesthetics at a fraction of the compute.</p>
<h3><strong>RAW-compatible LoRAs</strong></h3>
<p>Turbo is compatible with LoRAs trained on Krea 2 RAW, so the standard workflow is to train on RAW and run inference here. You can stack community LoRAs on top during on-site generation.</p>
<h3><strong>On-site generation</strong></h3>
<p>You can generate with Krea 2 Turbo directly on Civitai and add LoRAs on top. Weights are available upstream on Hugging Face under Krea's community license with permissive use; commercial licensing is available through opensource@krea.ai.</p>
<h3>Links</h3>
<ul><li>Weights: <a href="https://huggingface.co/krea/krea-2-turbo">huggingface.co/krea/krea-2-turbo</a></li><li>Technical report: <a href="https://www.krea.ai/blog/krea-2-technical-report">krea.ai/blog/krea-2-technical-report</a></li><li>Product: <a href="https://www.krea.ai">krea.ai</a></li></ul>

Krea 2 Turbo

krea2Turbo_v10.safetensors

v1.0

<p>Krea 2 RAW is the open-weights, undistilled checkpoint of Krea 2 - Krea AI's first foundation image model, trained from scratch with a focus on how an image feels rather than just what it contains. RAW is the full-guidance build with no step or CFG distillation, which gives it the highest quality ceiling of the family and makes it the right base for fine-tuning and LoRA training.</p>
<p><strong>Originally released by <a href="https://www.krea.ai">Krea AI</a> on Hugging Face.</strong> All credit for the model goes to the Krea team and the contributors listed below. Civitai is hosting a mirror so creators can generate with it and train on it on-site - please head to the <a href="https://huggingface.co/krea/krea-2-raw">original repo</a> for weights, the technical report, and to support the project directly.</p>
<h3>Built by</h3>
<p>Krea AI, with Sangwu Lee, Erwann Millon, Le Zhuo, Matthew Newton, Andrei Filatov, Abhinay Devarinti, Dazhi Zhong, Avram Djordjevic, Gabriel Menezes, Will Beddow, Titus Ebbecke, Mihai Petrescu, Owen Fahey, Gian Saß, Felix Gil, and Victor Perez.</p>
<h3><strong>Undistilled, full-guidance build</strong></h3>
<p>RAW runs with classifier-free guidance and no distillation, so it keeps the full character of the base model. Krea's recommended starting point is around 52 steps at CFG 3.5. It generates at up to 1024px and trades speed for the cleanest, most controllable output of the Krea 2 family. Reach for RAW when you want the maximum quality ceiling or a predictable base for training.</p>
<h3><strong>Built for fine-tuning and LoRAs</strong></h3>
<p>Because it is undistilled, RAW is the intended target for post-training, fine-tunes, and LoRA training. LoRAs trained on RAW also carry over to Krea 2 Turbo, so you can train once on the full model and run inference fast on the distilled build.</p>
<h3><strong>On-site generation</strong></h3>
<p>You can generate with Krea 2 RAW directly on Civitai and stack community LoRAs on top. Weights are available upstream on Hugging Face under Krea's community license with permissive use; commercial licensing is available through opensource@krea.ai.</p>
<h3>Links</h3>
<ul><li>Weights: <a href="https://huggingface.co/krea/krea-2-raw">huggingface.co/krea/krea-2-raw</a></li><li>Technical report: <a href="https://www.krea.ai/blog/krea-2-technical-report">krea.ai/blog/krea-2-technical-report</a></li><li>Product: <a href="https://www.krea.ai">krea.ai</a></li></ul>

Files with SHA256: f99bb0ff8e362b77342bc4994e0c50906fe7ef7074864b181b7d48d2fa6d03d7