Remove obsolete evidence and streamline model card

DATA_PROVENANCE.md

@@ -47,19 +47,6 @@ The bundle digest includes checkpoint metadata in addition to the format-2
 resume artifacts, preventing the data identity from being relabeled without
 changing the approved bundle identity.
 
-## Engineering gallery prompts
-
-The bundled paired contact sheet uses eight fixed project-authored prompts from
-the 256-prompt `clover-eval-v1` suite. It is evaluation input, not training
-data. Each row fixes the prompt and seed and compares the pinned starting model
-on the left with this Stage B checkpoint on the right. The contact sheet
-SHA-256 is
-`8653d1105b7b0c56e2385a127336dbe9b3a1a03c8518edb4934353a9d8e13bfa`.
-
-This subset checks that the pipeline produces finite, nonblank images. It does
-not establish representative quality, prompt alignment, diversity, fairness,
-or human preference.
-
 ## Foundational upstream provenance limitation
 
 The 1,000-pair manifest fully describes only the additional Clover calibration

README.md

@@ -61,32 +61,18 @@ widget:
 
 ![Clover Image Tiny mosaic banner](assets/clover-image-tiny-banner.png)
 
-A compact 512×512 text-to-image model you can run locally on iPhone, macOS,
-Windows, or Linux.
-
-**323,384,964 denoiser parameters · about 1.67 GB · 4–100 inference steps ·
-PyTorch/Diffusers**
-
 Clover Image Tiny 🤗 is an SD-1.4-class 512×512 diffusion checkpoint distilled
 for compact local inference. It follows the conventional Stable Diffusion 1.x
 text-to-image pipeline contract rather than a modern large-model architecture;
 results vary with the prompt, seed, scheduler, and number of denoising steps.
 
-The small-model comparison below is intentionally candid: Clover is not
-presented as a quality winner. Its distinction is the complete, practical
-package around a compact denoiser—local Python inference, Core ML/iPhone
-integration, linked style adapters, prompt-linked examples, and a model card
-with enough provenance to reproduce the documented paths.
-
 [**Try Clover Image Tiny in the live ZeroGPU demo →**](https://huggingface.co/spaces/neonforestmist/Clover-Image-Tiny-Demo)
 
 [**Explore the native iPhone/Core ML implementation →**](https://github.com/neonforestmist/Clover-Image-Tiny-iOS)
 
 The demo exposes prompt, negative prompt, seed, guidance, dimensions,
 scheduler, and 4–100 conventional Diffusers inference steps. It creates one
-image per request and keeps the packaged safety checker enabled. The Hugging
-Face model pages carry the model cards, tags, prompt galleries, and links to
-the corresponding LoRA and Core ML releases.
+image per request and keeps the packaged safety checker enabled.
 
 ## 1. Overview
 
@@ -105,24 +91,8 @@ the corresponding LoRA and Core ML releases.
 
 The package figure includes the text encoder, VAE, tokenizer/configuration, and
 the enabled upstream safety checker; it is therefore larger than the denoiser
-alone. The component sizes are a practical way to understand the footprint,
-not a claim that every byte is active in every runtime.
-
-### Why it stands out
-
-- **A small-model target with a complete workflow.** The 323.4M-parameter
-  denoiser is paired with a conventional Diffusers API, deterministic seeds,
-  scheduler controls, a safety path, and offline generation after the initial
-  download.
-- **Designed for local surfaces.** The same release is documented for Apple
-  silicon, CUDA, CPU, and an iPhone/Core ML path, with the heavier resources
-  split into versioned Hugging Face repositories.
-- **An extensible style family.** Monet, Pointillism, and Watercolor Anime
-  adapters are linked directly from the examples and published as both
-  Diffusers LoRAs and Core ML variants.
-- **Clear trade-offs.** The benchmark makes the quality/runtime limits visible
-  instead of hiding them behind a frontier-model comparison. The value here is
-  compactness, portability, and an unusually integrated 🤗 release surface.
+alone. Component sizes are approximate runtime-footprint context, not a claim
+that every byte is active in every backend.
 
 ## Contents
 
@@ -362,16 +332,16 @@ Run `python model/examples/generate.py --help` for the complete CLI reference.
 
 | System | Automatic backend | Precision | Current evidence |
 |---|---|---|---|
-| iPhone (iOS 17+) | Core ML | mixed/compiled | Native project and chunked download path included |
+| iPhone (iOS 17+) | Core ML | mixed/compiled | GitHub project and chunked download path linked above |
 | Apple-silicon Mac | MPS | fp16 | Measured locally on an M4 Pro |
 | Windows/Linux with NVIDIA | CUDA | fp16 | Supported code path; performance not measured |
 | CPU-only macOS/Windows/Linux | CPU | fp32 | Supported code path; performance not measured |
 | Windows AMD/DirectML | — | — | No packaged DirectML path |
 
-The model package itself is about 1.67 GB. Keep at least 2 GB free for the
-model alone and additional room for the Python environment and caches; no
-formal total-install minimum has been measured. Larger images and batches need
-more memory; lower `--width`, `--height`, or `--num-images` if necessary.
+Keep at least 2 GB free for the model alone and additional room for the Python
+environment and caches; no formal total-install minimum has been measured.
+Larger images and batches need more memory; lower `--width`, `--height`, or
+`--num-images` if necessary.
 
 The measured Mac reference used a 24 GB Apple M4 Pro and completed one 512×512
 image in 18.21 seconds with fp16 MPS. Its process-lifetime maximum RSS was
@@ -428,10 +398,9 @@ and distilled with a frozen
 teacher. It is a genuinely modified checkpoint, but it was not trained from
 random initialization.
 
-This repository contains the conventional PyTorch/Diffusers checkpoint plus
-reproducible Core ML conversion and iPhone app source. The downloadable Core ML
-artifacts and style adapters are versioned in the separate repositories linked
-above.
+This repository contains the PyTorch/Diffusers checkpoint. Core ML artifacts,
+style adapters, and the companion iOS project are versioned separately and
+linked above.
 
 ## 10. Quality and known behavior
 
@@ -520,8 +489,4 @@ does not grant a downstream reuse license for it.
 | Validated Stage B source-package checksums SHA-256 | `d9a28d5fe6f5b675ee1b9db52e6d0493c8d3d357bb824eac590911acbd5c3ebc` |
 | Builder source commit | `9f5ce495fcb88238ec7fdc33204fa42ec9690c37` |
 
-The local MPS reference evidence is bundled at
-`evidence/clover-image-tiny-local-mps-library-seed-1469.json`. Its image
-SHA-256 is
-`f8830346f2a9c2b9a8c2a01d8f90e6925c93d667c1bcf998aa904a150589a742`.
 `checksums.json` covers every packaged file.

checksums.json

@@ -1,20 +1,16 @@
 {
-  "DATA_PROVENANCE.md": "d0be84c8412aa9766c2477e145c3c4e9c7ff5beaf8116de5acc8d05e6616f857",
+  "DATA_PROVENANCE.md": "f0bc0235617375d25b26b8106f9a915f78ca641a4e9d62543c54a49d53fc558f",
   "LICENSE": "be351ebe7ac01bcdbb018639aadcfd38f136b7dc3f2a3d4d3a24db51d1b210ef",
   "LICENSE-CODE": "e26a0375b714267325c27905ba947fdc41ebc0b7a36940a49ae12379ed6208d6",
   "LICENSE-MODEL-CREATIVEML-OPENRAIL-M.txt": "be351ebe7ac01bcdbb018639aadcfd38f136b7dc3f2a3d4d3a24db51d1b210ef",
   "MODEL_DATA_LICENSES.md": "39501a1246aff094fcc987a548f7e8bd750dd21900b43c5a2e8cbcab305bb0b1",
-  "README.md": "beb79bcda817f6af19a70fd2fcb11657cd456fa4b3a83fdaafad3330d3cf18d7",
+  "README.md": "0e645c8af038276c0dc21722316c4ed61b64dbd37814a753e0c194519a3e2340",
   "assets/clover-image-tiny-banner.png": "c3d5c0243ebd0962263187fd54ea94e7646870a7c6e52ece620e958a43b827a3",
-  "assets/clover-image-tiny-local-mps-library-seed-1469.png": "f8830346f2a9c2b9a8c2a01d8f90e6925c93d667c1bcf998aa904a150589a742",
-  "assets/clover-image-tiny-paired-contact-sheet.png": "8653d1105b7b0c56e2385a127336dbe9b3a1a03c8518edb4934353a9d8e13bfa",
-  "evidence/clover-image-tiny-local-mps-library-seed-1469.json": "1ddd86de0be992987214266720e0f341f25791402aae637065d6d09a6ea67b27",
   "evidence/stage-b-inference-checksums.json": "d9a28d5fe6f5b675ee1b9db52e6d0493c8d3d357bb824eac590911acbd5c3ebc",
   "examples/generate.py": "4cfba0d6f3f2a5a9d1090564be5b618d06b757ef258ec7cfcff0523353e1466b",
   "feature_extractor/preprocessor_config.json": "205d45875859846dc1ca211b9a19f5db72f47e953b396954ee34d48d8e95c3c6",
   "model_index.json": "792073e269e5caff40b3f8c553387540c17a5d900ed0e9cbfab309d650e708dd",
   "requirements.txt": "9dbb74869a34e3b610f737bce8a9d2a20691fd0fa416cf6bb42354b78e0a3861",
-  "research_preview.json": "3ee097bdf9ab47f7897df545bb91096ed054a874adaab7310d32b1968496d032",
   "safety_checker/config.json": "241bd8fb1ba6feff0d7421f7af0f85743711c5d76353626f71f7e2cc8009ac7c",
   "safety_checker/model.safetensors": "57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6",
   "scheduler/scheduler_config.json": "184bc33ed887951dd86e37f20c878710c4e18e1c5fd4461256a3825679b53d15",

evidence/clover-image-tiny-local-mps-library-seed-1469.json

@@ -1 +0,0 @@
-{"generation":{"denoiser_calls":51,"device":"mps","dtype":"float16","elapsed_seconds":18.208059416996548,"guidance_scale":7.5,"height":512,"negative_prompt":"","num_inference_steps":50,"prompt":"a compact modern library with arched windows","scheduler":"PNDMScheduler","seed":1469,"width":512},"image":{"filename":"library-seed-1469.png","format":"PNG","height":512,"mode":"RGB","pixel_mean":114.8316281636556,"pixel_standard_deviation":69.02280620757928,"sha256":"f8830346f2a9c2b9a8c2a01d8f90e6925c93d667c1bcf998aa904a150589a742","width":512},"kind":"clover-stage-b-local-generation-evidence","limitations":{"cross_hardware_pixel_identity":"not_claimed","iphone_or_coreml_result":false,"release_quality":"not_measured"},"memory":{"process_lifetime_max_rss_bytes":631341056,"rss_after_bytes":631341056,"rss_before_bytes":402030592,"sampled_process_peak_rss_bytes":624803840,"sampling_interval_seconds":0.05},"model":{"checkpoint_bundle_checksum":"384b6515f5f26838aea33ec9a941e06610a20764f0b8637c8b7b0667bfc0d447","checkpoint_checksum":"4a5b99ff18478742528a0d31c97dcee939b166a51be858721d40ad5984110893","config_hash":"80cf9395d1f587dc0c1d440d9f5b55c55c20703187998509bb306d19d463f597","dataset_manifest_checksum":"50c1249f1cb0d8d690a9acc451ca10c9432eb5a7f4e26f34acb5462096e72322","experiment_id":"clover-kd-20260712T050925Z-01KXABNHP0","optimizer_step":500,"package_checksums_sha256":"d9a28d5fe6f5b675ee1b9db52e6d0493c8d3d357bb824eac590911acbd5c3ebc"},"runtime":{"platform":"macOS-27.0-arm64-arm-64bit","python":"3.12.13","torch":"2.7.0"},"safety":{"host_review_note":"Automated filtering is imperfect; review generated output before sharing.","nsfw_content_detected":false,"packaged_checker_invoked":true},"schema_version":1}

research_preview.json

@@ -1,189 +0,0 @@
-{
-  "build": {
-    "repository_commit": "9f5ce495fcb88238ec7fdc33204fa42ec9690c37",
-    "sources": {
-      "LICENSE-CODE": {
-        "sha256": "e26a0375b714267325c27905ba947fdc41ebc0b7a36940a49ae12379ed6208d6",
-        "tracked_at_commit": true
-      },
-      "LICENSE-MODEL-CREATIVEML-OPENRAIL-M.txt": {
-        "sha256": "be351ebe7ac01bcdbb018639aadcfd38f136b7dc3f2a3d4d3a24db51d1b210ef",
-        "tracked_at_commit": true
-      },
-      "assets/model-examples/clover-image-tiny-local-mps-v1/library-seed-1469.png": {
-        "sha256": "f8830346f2a9c2b9a8c2a01d8f90e6925c93d667c1bcf998aa904a150589a742",
-        "tracked_at_commit": true
-      },
-      "assets/model-examples/clover-image-tiny-local-mps-v1/library-seed-1469.png.json": {
-        "sha256": "1ddd86de0be992987214266720e0f341f25791402aae637065d6d09a6ea67b27",
-        "tracked_at_commit": true
-      },
-      "hf/stage_b_preview/DATA_PROVENANCE.md": {
-        "sha256": "d0be84c8412aa9766c2477e145c3c4e9c7ff5beaf8116de5acc8d05e6616f857",
-        "tracked_at_commit": true
-      },
-      "hf/stage_b_preview/MODEL_DATA_LICENSES.md": {
-        "sha256": "39501a1246aff094fcc987a548f7e8bd750dd21900b43c5a2e8cbcab305bb0b1",
-        "tracked_at_commit": true
-      },
-      "hf/stage_b_preview/README.template.md": {
-        "sha256": "48da494a6278ba161cea93c62e4d04bbc7a48c5da46f9d7568c262329ea8e366",
-        "tracked_at_commit": true
-      },
-      "hf/stage_b_preview/assets/clover-image-tiny-banner.png": {
-        "sha256": "c3d5c0243ebd0962263187fd54ea94e7646870a7c6e52ece620e958a43b827a3",
-        "tracked_at_commit": true
-      },
-      "hf/stage_b_preview/examples/generate.py": {
-        "sha256": "4cfba0d6f3f2a5a9d1090564be5b618d06b757ef258ec7cfcff0523353e1466b",
-        "tracked_at_commit": true
-      },
-      "hf/stage_b_preview/requirements.txt": {
-        "sha256": "9dbb74869a34e3b610f737bce8a9d2a20691fd0fa416cf6bb42354b78e0a3861",
-        "tracked_at_commit": true
-      },
-      "scripts/build_hf_stage_b_preview.py": {
-        "sha256": "340b8db4f06ab7fbba107db1242de5ae3938cb0151b97908831695350df4c980",
-        "tracked_at_commit": true
-      },
-      "scripts/publish_hf_stage_b_preview.py": {
-        "sha256": "4ff6ea2e0f4d04ec1b2c7de04b0ba831fefc65faae0a8fa362ada52bbb820916",
-        "tracked_at_commit": true
-      },
-      "scripts/validate_hf_stage_b_preview.py": {
-        "sha256": "6c521dc2dd332ccbafd2764ee2d1ee3f618901b5061e2efaca56534dbdd17be5",
-        "tracked_at_commit": true
-      },
-      "src/clover_image/release_licenses.py": {
-        "sha256": "371fdf7f30c2e0268d417c6be3e5edaaf662372685eeb19831bed49d096f9557",
-        "tracked_at_commit": true
-      },
-      "src/clover_image/stage_b_inference.py": {
-        "sha256": "2c4a92f2af4eb4ec633b8b163fbd129efe4a63b52055f9fadd5e283020ffd6f7",
-        "tracked_at_commit": true
-      },
-      "src/clover_image/stage_b_preview.py": {
-        "sha256": "7a769e4e6098580c4235c56ff29ab3cc17496d5b6d528be425ee8000cc86e849",
-        "tracked_at_commit": true
-      }
-    }
-  },
-  "checkpoint": {
-    "checkpoint_bundle_checksum": "384b6515f5f26838aea33ec9a941e06610a20764f0b8637c8b7b0667bfc0d447",
-    "checkpoint_checksum": "4a5b99ff18478742528a0d31c97dcee939b166a51be858721d40ad5984110893",
-    "config_hash": "80cf9395d1f587dc0c1d440d9f5b55c55c20703187998509bb306d19d463f597",
-    "experiment_id": "clover-kd-20260712T050925Z-01KXABNHP0",
-    "optimizer_step": 500
-  },
-  "data": {
-    "dataset_id": "Spawning/PD3M",
-    "dataset_license_id": "CDLA-Permissive-2.0",
-    "dataset_revision": "2a5eb24a8dccf245acd8e56341761aee06da0bdf",
-    "manifest_sha256": "50c1249f1cb0d8d690a9acc451ca10c9432eb5a7f4e26f34acb5462096e72322",
-    "raw_data_bundled": false,
-    "record_count": 1000,
-    "split_counts": {
-      "test": 10,
-      "train": 973,
-      "validation": 17
-    }
-  },
-  "gallery": {
-    "bundled_path": "assets/clover-image-tiny-paired-contact-sheet.png",
-    "contact_sheet_sha256": "8653d1105b7b0c56e2385a127336dbe9b3a1a03c8518edb4934353a9d8e13bfa",
-    "evaluation_scope": "eight-prompt-engineering-health-subset",
-    "human_review": "not_measured",
-    "image_pair_count": 8,
-    "kind": "stage-b-paired-engineering-gallery",
-    "quality_decisional": false,
-    "source_completion_sha256": "344823dd2b7816fcca8119344de84a3e214b399d9cb267600a0d369dfc7a20df",
-    "source_records_sha256": "36fecf6eebe43b7baba7ca7b9c57de32343b74d0075b8dc83cfb6062692e7315",
-    "source_report_sha256": "d09ca159c4face6d4ab895f67afe5c52fa03adf2647d01121527be4f501f4c71",
-    "status": "validated"
-  },
-  "hf_repo_id": "neonforestmist/Clover-Image-Tiny",
-  "kind": "clover-stage-b-hf-research-preview",
-  "licenses": {
-    "code": {
-      "id": "Apache-2.0",
-      "path": "LICENSE-CODE",
-      "sha256": "e26a0375b714267325c27905ba947fdc41ebc0b7a36940a49ae12379ed6208d6"
-    },
-    "model_weights": {
-      "id": "CreativeML OpenRAIL-M",
-      "path": "LICENSE-MODEL-CREATIVEML-OPENRAIL-M.txt",
-      "sha256": "be351ebe7ac01bcdbb018639aadcfd38f136b7dc3f2a3d4d3a24db51d1b210ef"
-    }
-  },
-  "limitations": {
-    "foundational_data_provenance": "incomplete_upstream_per_record_evidence",
-    "human_review": "not_measured",
-    "quality_evaluation": "not_measured"
-  },
-  "metadata_sha256": "faa5ac18488ff0a0c37da1471194395c841a27086056d31cf2b7b56cc758c214",
-  "presentation": {
-    "model_card_banner": {
-      "bundled_path": "assets/clover-image-tiny-banner.png",
-      "downstream_reuse_license": "not_granted_by_this_package",
-      "format": "PNG",
-      "generation_provenance": "not_claimed",
-      "height": 922,
-      "mode": "RGBA",
-      "publication_authorization": "explicit_user_request",
-      "publication_scope": "public_hugging_face_model_repository",
-      "quality_decisional": false,
-      "sha256": "c3d5c0243ebd0962263187fd54ea94e7646870a7c6e52ece620e958a43b827a3",
-      "size_bytes": 4584745,
-      "source": "user_supplied",
-      "width": 2302
-    }
-  },
-  "release_ready": false,
-  "runtime_contract": {
-    "denoiser_calls": 51,
-    "guidance_scale": 7.5,
-    "height": 512,
-    "negative_prompt": "",
-    "num_inference_steps": 50,
-    "pipeline": "StableDiffusionPipeline",
-    "scheduler": "PNDMScheduler",
-    "width": 512
-  },
-  "schema_version": 2,
-  "source_package": {
-    "checksums_path": "evidence/stage-b-inference-checksums.json",
-    "checksums_sha256": "d9a28d5fe6f5b675ee1b9db52e6d0493c8d3d357bb824eac590911acbd5c3ebc",
-    "validation": {
-      "checkpoint_bundle_checksum": "384b6515f5f26838aea33ec9a941e06610a20764f0b8637c8b7b0667bfc0d447",
-      "checkpoint_checksum": "4a5b99ff18478742528a0d31c97dcee939b166a51be858721d40ad5984110893",
-      "config_hash": "80cf9395d1f587dc0c1d440d9f5b55c55c20703187998509bb306d19d463f597",
-      "dataset_manifest_checksum": "50c1249f1cb0d8d690a9acc451ca10c9432eb5a7f4e26f34acb5462096e72322",
-      "experiment_id": "clover-kd-20260712T050925Z-01KXABNHP0",
-      "file_count": 17,
-      "guidance_scale": 7.5,
-      "inference_steps": 50,
-      "optimizer_step": 500,
-      "package_checksums_sha256": "d9a28d5fe6f5b675ee1b9db52e6d0493c8d3d357bb824eac590911acbd5c3ebc",
-      "parameter_count": 323384964,
-      "resolution": 512,
-      "status": "valid",
-      "total_size_bytes": 1669943733,
-      "upstream_model_id": "nota-ai/bk-sdm-tiny-2m",
-      "upstream_revision": "aad3e0e8ba61b7cb9f64869dc4e586f8ad9d3665",
-      "weight_dtype": "float16"
-    }
-  },
-  "status": "research_preview",
-  "training_stage": "stage_b_knowledge_distillation",
-  "upstream": {
-    "student": {
-      "model_id": "nota-ai/bk-sdm-tiny-2m",
-      "revision": "aad3e0e8ba61b7cb9f64869dc4e586f8ad9d3665"
-    },
-    "teacher": {
-      "model_id": "CompVis/stable-diffusion-v1-4",
-      "revision": "133a221b8aa7292a167afc5127cb63fb5005638b"
-    }
-  },
-  "usage_label": "RESEARCH PREVIEW - PRODUCTION PILOT - NOT RELEASE-READY"
-}