Add files using upload-large-folder tool

MD5SUMS

@@ -0,0 +1,3 @@
+d8d69fba0bafdda9cfd561107e28c518  realvisxl-v40-lightning-fp16.safetensors
+d2799fb3cb748982fa1932278179cc88  ip-adapter-plus-face_sdxl_vit-h.safetensors
+ed38a0b229471ee0c1826a6ddb658083  ip_adapter_clip_vision_vith.safetensors

README.md

@@ -0,0 +1,120 @@
+---
+license: openrail++
+license_name: tokforge-sdxl-ipadapter-bundle
+tags:
+- text-to-image
+- image-to-image
+- stable-diffusion
+- stable-diffusion-xl
+- sdxl
+- ip-adapter
+- realvisxl
+- reference-image
+- identity
+- multi-subject
+- safetensors
+- stable-diffusion-cpp
+- tokforge
+base_model:
+- SG161222/RealVisXL_V4.0_Lightning
+- h94/IP-Adapter
+pipeline_tag: text-to-image
+---
+
+# TokForge — SDXL IP-Adapter (Reference Identity) bundle
+
+The **highest-fidelity reference-identity** image route for the [TokForge](https://tokforge.ai)
+Android app, and the **clean multi-subject** path. Attach a photo of a person (or two),
+then render **that person** in any scene (*"me as a superhero, unmasked, face visible"*).
+The **plus-face** IP-Adapter transfers the **face only** while the **prompt drives the
+whole scene**. SDXL's stronger plus-face transfer (vs SD1.5) gives sharper single-subject
+identity, and makes the regional-mask **two-subject** path produce two distinct recognizable
+faces.
+
+This bundle runs on the on-device [`stable-diffusion.cpp`](https://github.com/leejet/stable-diffusion.cpp)
+engine (TokForge's IP-Adapter port) on **CPU** and **Adreno OpenCL**. Full SDXL is heavier
+than the SD1.5 IP-Adapter tier — this is offered on **16 GB-class** phones. For 8 GB phones,
+use the lighter [`darkmaniac7/TokForge-SD15-IPAdapter`](https://huggingface.co/darkmaniac7/TokForge-SD15-IPAdapter)
+tier instead.
+
+## Files
+
+| File | Size | License | Contents |
+|------|------|---------|----------|
+| `realvisxl-v40-lightning-fp16.safetensors` | ~6.9 GB | OpenRAIL++ | **RealVisXL V4.0 Lightning** (SDXL photoreal finetune) — dual CLIP text encoders + UNet + VAE in one self-contained **f16** sd.cpp safetensors |
+| `ip-adapter-plus-face_sdxl_vit-h.safetensors` | ~848 MB | Apache-2.0 | IP-Adapter **plus-face** SDXL (`h94/IP-Adapter`) — 16-token image_proj Resampler + 70 decoupled cross-attn layers (`cross_attention_dim` 2048) |
+| `ip_adapter_clip_vision_vith.safetensors` | ~2.5 GB | MIT | OpenCLIP **ViT-H-14** image encoder (1280 hidden, 32 layers). The plus-face path needs ViT-H, **not** bigG — the same encoder the SD1.5 plus-face bundle ships |
+
+`manifest.json` and `MD5SUMS` carry the integrity hashes + render defaults.
+
+### Why this base, and why f16 (not Q4)
+
+The base is **RealVisXL V4.0 Lightning** — the same self-contained SDXL safetensors the
+TokForge "RealVisXL SDXL Quality" tier ships, a strong photoreal SDXL finetune distilled
+for a **few-step** (6-step) Lightning floor. It is kept at **f16** (full precision) so the
+IP-Adapter's decoupled cross-attention and the face Resampler keep **subject quality** high.
+A `q4_0` base measurably weakens the transferred identity, so this bundle deliberately uses f16
+(matching the SD1.5 tier's quality choice).
+
+### Why plus-face + ViT-H (not the base SDXL adapter + bigG)
+
+The standard `ip-adapter_sdxl` projects the whole pooled CLIP-**bigG** embedding → it drags the
+reference's *entire scene* through. The **plus-face** variant (`ip-adapter-plus-face_sdxl_vit-h`)
+runs a 16-token Resampler over the **ViT-H** penultimate hidden state → it extracts the **face
+only**, so identity is preserved while the **prompt** controls the scene. Because this adapter is
+the `_vit-h` build (`image_proj.latents` shape `[1, 16, 1280]`), it pairs with the **ViT-H**
+encoder (1280 hidden) — **not** the bigG encoder (1664 hidden) the base SDXL adapter uses. The
+TokForge sd.cpp IP-Adapter loader auto-detects plus-face by `image_proj.latents` and the SDXL
+adapter config (2048-dim, 70 layers) by the SDXL base.
+
+## How TokForge uses it
+
+In the app (16 GB+ phones): **Image** model picker → download **"SDXL IP-Adapter (Reference
+Identity)"** → attach a face photo as a reference under chat → prompt the scene. The engine is
+invoked as:
+
+```bash
+sd -M img_gen \
+   -m realvisxl-v40-lightning-fp16.safetensors \
+   -p "as a superhero, unmasked, face visible, detailed face" \
+   -n "<strong negative>" \
+   --clip_vision ip_adapter_clip_vision_vith.safetensors \
+   --ip-adapter ip-adapter-plus-face_sdxl_vit-h.safetensors \
+   --ip-adapter-image <your_face.jpg> \
+   --ip-adapter-scale 0.75 \
+   --cfg-scale 2.0 --sampling-method euler --scheduler discrete \
+   --steps 6 -H 1024 -W 1024
+```
+
+### Recommended render settings
+
+| Setting | Value |
+|---------|-------|
+| sampler | `euler` |
+| scheduler | `discrete` |
+| steps | `6` (Lightning few-step floor) |
+| cfg-scale | `2.0` (Lightning low-CFG) |
+| ip-adapter-scale | `0.75` (keeps the scene with strong recognizable identity; lower ≈ more scene freedom, higher ≈ closer to the reference) |
+| resolution | `1024×1024` (SDXL native) |
+
+> Plus-face transfers the **face only**, so the rendered face must stay **visible and
+> unobstructed** for a recognizable identity. Keep the face in frame ("unmasked, face visible,
+> detailed face, looking at viewer") — the app appends this cue automatically.
+
+## Licenses
+
+This is an aggregate of three independently-licensed components — each retains its own license:
+
+- **RealVisXL V4.0 Lightning base** (`realvisxl-v40-lightning-fp16.safetensors`) — **OpenRAIL++** ([SG161222/RealVisXL_V4.0_Lightning](https://huggingface.co/SG161222/RealVisXL_V4.0_Lightning), the SDXL `openrail++` license). Use must comply with the OpenRAIL++ use-based restrictions.
+- **IP-Adapter plus-face (SDXL, ViT-H)** (`ip-adapter-plus-face_sdxl_vit-h.safetensors`) — **Apache-2.0** ([h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter)).
+- **OpenCLIP ViT-H-14 image encoder** (`ip_adapter_clip_vision_vith.safetensors`) — **MIT** (OpenCLIP / LAION ViT-H-14).
+
+> The non-commercial **IP-Adapter-FaceID** / InsightFace path is **NOT** used here — only the
+> Apache-2.0 base + plus-face adapters from `h94/IP-Adapter`.
+
+## Provenance
+
+- Base: `realvisxl-v40-lightning-fp16.safetensors`, the self-contained sd.cpp SDXL safetensors
+  built from `SG161222/RealVisXL_V4.0_Lightning` (the same base the TokForge RealVisXL SDXL tier ships).
+- Adapter + image encoder copied verbatim from `h94/IP-Adapter`
+  (`sdxl_models/ip-adapter-plus-face_sdxl_vit-h.safetensors`, `models/image_encoder/model.safetensors`).

ip-adapter-plus-face_sdxl_vit-h.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677ad8860204f7d0bfba12d29e6c31ded9beefdf3e4bbd102518357d31a292c1
+size 847517512

ip_adapter_clip_vision_vith.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca9667da1ca9e0b0f75e46bb030f7e011f44f86cbfb8d5a36590fcd7507b030
+size 2528373448

manifest.json

@@ -0,0 +1,28 @@
+{
+  "name": "TokForge-SDXL-IPAdapter",
+  "family": "sdxl_ipadapter",
+  "engine": "stable-diffusion.cpp",
+  "base_model": "SG161222/RealVisXL_V4.0_Lightning",
+  "adapter": "h94/IP-Adapter — ip-adapter-plus-face_sdxl_vit-h (plus-face, SDXL)",
+  "image_encoder": "OpenCLIP ViT-H-14 (h94/IP-Adapter image_encoder)",
+  "format": "safetensors",
+  "precision": "f16",
+  "native_resolution": 1024,
+  "default_steps": 6,
+  "sampler": "euler",
+  "scheduler": "discrete",
+  "cfg_scale": 2.0,
+  "default_ip_adapter_scale": 0.75,
+  "cross_attention_dim": 2048,
+  "ip_cross_attn_layers": 70,
+  "licenses": {
+    "base": "openrail++",
+    "adapter": "apache-2.0",
+    "image_encoder": "mit"
+  },
+  "files": [
+    {"name": "realvisxl-v40-lightning-fp16.safetensors", "size": 6938040286, "md5": "d8d69fba0bafdda9cfd561107e28c518", "role": "diffusion_base", "contents": "RealVisXL V4.0 Lightning SDXL — dual CLIP text encoders + SDXL UNet + VAE (single self-contained sd.cpp safetensors)"},
+    {"name": "ip-adapter-plus-face_sdxl_vit-h.safetensors", "size": 847517512, "md5": "d2799fb3cb748982fa1932278179cc88", "role": "ip_adapter", "contents": "IP-Adapter plus-face (SDXL, ViT-H): 16-token image_proj Resampler + 70 decoupled cross-attn to_k_ip/to_v_ip layers (cross_attention_dim 2048)"},
+    {"name": "ip_adapter_clip_vision_vith.safetensors", "size": 2528373448, "md5": "ed38a0b229471ee0c1826a6ddb658083", "role": "clip_vision", "contents": "OpenCLIP ViT-H-14 image encoder (1280 hidden, 32 layers) — the SAME encoder the SD1.5 plus-face bundle uses; plus-face_sdxl_vit-h needs ViT-H, not bigG"}
+  ]
+}

realvisxl-v40-lightning-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec48b5b0728292d09f7b91dcf644b3f1654d4335e9982711c6a6028f9718da0
+size 6938040286