Kroma v0.2 Released: Full Krea 2 Fine-tune with Turbo Support for ComfyUI
bdsqlsz · x · 2026-08-09
Kroma v0.2 has been released on Hugging Face, a full fine-tuned text-to-image model based on Krea 2. This version merges the Krea 2 Turbo delta, offering fine-tuned quality and Turbo generation speed in a single file.
Key Details:
- No Base Model Required: Distributed as a full diffusion model checkpoint, eliminating the need for separate base models or LoRAs.
- ComfyUI Settings: Requires the Krea 2 Text Encoder and VAE. Recommended sampling settings: 8-12 steps, CFG 1.0–1.5, Shift 1.15.
- Open Source: Released under the MIT license.
Related event: Kroma v0.2 Released: Full Fine-Tuned Model Based on Krea 2(2 posts)→
More from Multimodal
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16
- 'Celestial Ocean Reverie' prompt template blends starry skies with dreamlike seascapes — LudovicCreator · 2026-10-16
- 'Thicc Lil' Red': an AI-made musical meme reimagining Little Red Riding Hood — bennash · 2026-10-16
- CoWorld Reasoner uses an evolving video world model as a visual reasoning engine — ModalityDance · 2026-10-16
- PixelLab tackles ComfyUI pain points: model dedup, image triage, workflow repair — SmartRick137 · 2026-10-16
- Everything is instantly a playable game: browser Roadster Rally demo — bennash · 2026-10-16