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
- Seedance 2.5 Launches on Higgsfield with 30-Second Video Generation — CurieuxExplorer · 2026-08-09
- MiniMax H3 in ComfyUI Generates 'Mr. Bean – The Lost Mini Episode' — AxonkaiLab · 2026-08-09
- Krea2 Turbo bbox Model Released for ComfyUI and HF Space — Amazing_Painter_7692 · 2026-08-09
- Grok Image 2.0 Tested: Fancy Segmentation Enables Precise Image Editing — mark_k · 2026-08-09
- RTX 5060Ti Test: Generating Cinematic Action Video with Minimax H3 Turbo — AppointmentOk972 · 2026-08-09
- MiniMax H3 Video Acceleration: 4-Step LoRA & Decoupled Audio/Video Scheduling — wjc_5 · 2026-08-09