@sogni-ai/sogni-client 5.4.0 → 5.5.0

package/AGENTS.md

@@ -73,6 +73,8 @@ Public chat and workflow media rules:
 
 This is the **Sogni SDK for JavaScript/Node.js** - a TypeScript client library for the Sogni Supernet, a DePIN protocol for creative AI inference. The SDK supports image generation (Stable Diffusion, Flux, Flux.2, Z-Image / Z-Image Turbo, Krea 2 Turbo, Krea 2 Identity Edit, Chroma v.46 Flash / v.48 Detail / Chroma1-HD, Qwen image-edit models, GPT Image 2, plus community fine-tunes such as Dark Beast Z-Image Turbo v9, Dark Beast KREA 2, Dark Beast Krea 2 Identity Edit, and One Obsession v22), video generation (WAN 2.2, LTX-2.3, Seedance 2.0, HappyHorse 1.1), audio generation (ACE-Step 1.5), LLM chat with tool calling, hosted creative tools, durable creative workflows, replay records, and multimodal vision chat (Qwen3.6 35B VLM, default `qwen3.6-35b-a3b-gguf-iq4xs`). The model catalog is discovered dynamically at runtime (`sogni.projects.getAvailableModels()`); model ids listed here are illustrative.
 
+Choosing an image-edit model: pick by what the edit has to preserve, not by step count or quality tier. When a person or character must stay recognisable through the edit — style transfer, makeover, clothing or person swap, face swap, new pose or expression, character sheet — use Krea 2 Identity Edit (`krea2_identity_edit_v1_2`, or `dark_beast_krea2_identity_edit_v1_2` uncensored) with 1-2 context images. For general-purpose editing — photo transforms, in-image text, multi-person changes, combining up to 3 references — use a Qwen image-edit model. A higher-step general-purpose editor does not beat the identity model at a likeness task; it reinterprets the subject instead of preserving it. See `llms.txt` for parameters.
+
 Runtime and packaging:
 
 - Node.js `>=22` is required by `package.json`.

package/CHANGELOG.md

@@ -1,3 +1,10 @@
+# [5.5.0](https://github.com/Sogni-AI/sogni-client/compare/v5.4.0...v5.5.0) (2026-08-06)
+
+
+### Features
+
+* **docs:** guide image-edit model choice by intent ([d8903cd](https://github.com/Sogni-AI/sogni-client/commit/d8903cd23644847f27258aedee603c7a02e8fa3f))
+
 # [5.4.0](https://github.com/Sogni-AI/sogni-client/compare/v5.3.3...v5.4.0) (2026-08-04)
 
 

package/dist/version.d.ts

@@ -1 +1 @@
-export declare const LIB_VERSION = "5.4.0";
+export declare const LIB_VERSION = "5.5.0";

package/dist/version.js

@@ -3,5 +3,5 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.LIB_VERSION = void 0;
 // AUTO-GENERATED by scripts/generate-version.mjs — do not edit.
 // Source of truth: package.json version.
-exports.LIB_VERSION = '5.4.0';
+exports.LIB_VERSION = '5.5.0';
 //# sourceMappingURL=version.js.map

package/dist-esm/version.js

@@ -1,4 +1,4 @@
 // AUTO-GENERATED by scripts/generate-version.mjs — do not edit.
 // Source of truth: package.json version.
-export const LIB_VERSION = '5.4.0';
+export const LIB_VERSION = '5.5.0';
 //# sourceMappingURL=version.js.map

package/llms-full.txt

@@ -434,12 +434,22 @@ RECOMMENDED MODELS:
 | z_image_turbo_bf16 | Ultra-fast | 8 | 1 | Fastest generation |
 | z_image_bf16 | Quality | 20 | 3 | High quality Z-Image generation |
 | krea2_turbo_fp8_scaled | Fast | 8 | 1 | Distilled few-step, strong in-image text, up to 2K |
-| krea2_identity_edit_v1_2 | Edit | 10 | 1 | Identity-preserving Krea 2 edit LoRA with 1-2 context images |
+| krea2_identity_edit_v1_2 | Edit | 10 | 1 | Best for transforming a person/character while keeping their likeness; 1-2 context images |
 | chroma1-hd_fp8_scaled | Quality | 26 | 3.8 | Final high-res Chroma (uncensored, LoRA-capable) |
 | flux2_dev_fp8 | Quality | 20 | 4 | Pro quality + up to 6 context images (also image edit) |
-| qwen_image_edit_2511_fp8_lightning | Edit | 4 | 1 | Multi-image context |
+| qwen_image_edit_2511_fp8_lightning | Edit | 4 | 1 | Fast general-purpose editing; multi-image context |
 | coreml-cyberrealistic_v70_768 | SD 1.5 | 20-40 | 7.5 | Photorealistic |
 
+CHOOSING AN IMAGE-EDIT MODEL: pick by what the edit has to preserve, not by step
+count or quality tier. If a person or character has to stay recognisable through
+the edit — style transfer, makeover, clothing or person swap, face swap, new pose
+or expression, character sheet — use krea2_identity_edit_v1_2 (or
+dark_beast_krea2_identity_edit_v1_2 for uncensored). For everything else — photo
+transforms, in-image text edits, multi-person changes, combining up to 3
+references — use a qwen_image_edit_2511 variant. A higher-step general-purpose
+editor does not beat the identity model at a likeness task; it reinterprets the
+subject instead of preserving it.
+
 COMMUNITY FINE-TUNES (uncensored; discover with sogni.projects.getAvailableModels()):
 | Model ID | Type | Steps | Guidance | Notes |
 |----------|------|-------|----------|-------|

package/llms.txt

@@ -209,7 +209,7 @@ The full catalog is dynamic — enumerate it at runtime with
 | `z_image_turbo_bf16` | Z-Image Turbo — ultra-fast 8-step (free-tier eligible) |
 | `z_image_bf16` | Z-Image — high quality 20-50 step |
 | `krea2_turbo_fp8_scaled` | Krea 2 Turbo — few-step, strong in-image text, up to 2K |
-| `krea2_identity_edit_v1_2` | Krea 2 Identity Edit LoRA v1.2 — identity-preserving edits with 1-2 reference images |
+| `krea2_identity_edit_v1_2` | Krea 2 Identity Edit LoRA v1.2 — best for transforming a person or character while keeping their likeness; 1-2 reference images |
 | `chroma-v.46-flash_fp8` | Chroma v.46 Flash — fast, high quality |
 | `chroma-v48-detail-svd_fp8` | Chroma v.48 Detail — high detail |
 | `chroma1-hd_fp8_scaled` | Chroma1-HD — final high-res Chroma (uncensored, LoRA-capable) |
@@ -226,9 +226,23 @@ Community fine-tunes (uncensored; pass the id directly):
 `dark_beast_krea2_identity_edit_v1_2` (Krea 2 identity edit LoRA),
 `one_obsession_v22_fp16` (Illustrious/anime, LoRA-capable).
 
-For identity-preserving edits, use `krea2_identity_edit_v1_2` or
-`dark_beast_krea2_identity_edit_v1_2` with 1-2 `contextImages`, `steps: 10`,
-and `guidance: 1`.
+### Choosing an image-edit model
+
+Pick by what the edit has to preserve, not by step count or quality tier.
+
+- **A person or character whose likeness must survive the edit** — use
+  `krea2_identity_edit_v1_2` (or `dark_beast_krea2_identity_edit_v1_2` for
+  uncensored) with 1-2 `contextImages`, `steps: 10`, and `guidance: 1`. This is
+  the right model for style transfers, makeovers, clothing or person swaps, face
+  swaps, new poses or expressions, and character sheets.
+- **Everything else** — use `qwen_image_edit_2511_fp8_lightning` (fast) or
+  `qwen_image_edit_2511_fp8`: general-purpose photo transforms, in-image text
+  edits, multi-person changes, and combining up to 3 reference images.
+
+A higher-step general-purpose editor does not beat the identity model at a
+likeness task — it reinterprets the subject instead of preserving it. When an
+edit both preserves a likeness and needs general-purpose work, run the identity
+model first, then edit its output.
 
 ---
 

package/package.json

@@ -3,7 +3,7 @@
   "publishConfig": {
     "access": "public"
   },
-  "version": "5.4.0",
+  "version": "5.5.0",
   "engines": {
     "node": ">=22"
   },

package/src/version.ts

@@ -1,3 +1,3 @@
 // AUTO-GENERATED by scripts/generate-version.mjs — do not edit.
 // Source of truth: package.json version.
-export const LIB_VERSION = '5.4.0';
+export const LIB_VERSION = '5.5.0';