Krea 2 Identity Edit LoRA Upgraded to v1.1
ostrisai · x · 2026-07-12
The `krea2-identity-edit` LoRA for Krea 2 has been upgraded to **v1.1**, bringing improved results over the previous version. The workflow shifted from the `comfyui-krea2edit` node (which accepted only **2 reference images**) to `ComfyUI-Krea2-Ostris-Edit`, which supports **3 reference images**. This allows simultaneous control over: - Character - Clothing - Scene The post also explains that while Krea 2 is fundamentally a **t2i model**, combining `krea2-identity-edit` with `ComfyUI-Krea2-Ostris-Edit` and the **Qwen3-VL text encoder** to fuse images and prompts enables the model to "see" reference images during generation, achieving an i2i / edit-like effect.
More from coding & agent
- Codex turns out 123 screensavers in one playful batch — intellectronica · 2026-07-21
- Grok Build adds `grok doctor`, resumable sessions and remote image paste — mark_k · 2026-07-21
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21