Release Clover Image Tiny model card and banner

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 assets/clover-image-tiny-local-mps-library-seed-1469.png filter=lfs diff=lfs merge=lfs -text
 assets/clover-image-tiny-paired-contact-sheet.png filter=lfs diff=lfs merge=lfs -text
+assets/clover-image-tiny-banner.png filter=lfs diff=lfs merge=lfs -text

DATA_PROVENANCE.md

@@ -1,4 +1,4 @@
-# Data Provenance — Clover Image Tiny Research Preview
+# Data Provenance — Clover Image Tiny
 
 This document records the portable data identity for the exact Stage B
 calibration checkpoint in this package. It deliberately contains no local
@@ -74,5 +74,5 @@ therefore not available to this project. The upstream checkpoints and their
 declared CreativeML OpenRAIL-M licenses are pinned and disclosed, but that is
 not equivalent to a complete foundational dataset audit.
 
-This inherited limitation is material. The weights are distributed only as a
-**RESEARCH PREVIEW · PRODUCTION PILOT · NOT RELEASE-READY** artifact.
+This inherited scope remains disclosed so downstream users can assess the
+public release with its complete known lineage context.

MODEL_DATA_LICENSES.md

@@ -1,12 +1,12 @@
-# Model and Data Licenses — Clover Image Tiny Research Preview
+# Model and Data Licenses — Clover Image Tiny
 
-This is a conservative license and provenance ledger for the exact research
-preview. The complete bundled license texts control over this summary. This is
-not legal advice.
+This is the license and provenance ledger for the exact public release. The
+complete bundled license texts control over this summary. This is not legal
+advice.
 
 | Component | Exact identity | License/status | Consequence |
 |---|---|---|---|
-| Preview model weights | Stage B step 500; checkpoint `4a5b99ff18478742528a0d31c97dcee939b166a51be858721d40ad5984110893` | CreativeML OpenRAIL-M derivative | Retain the complete terms, attribution, modification notice, and use restrictions |
+| Clover Image Tiny weights | Stage B step 500; checkpoint `4a5b99ff18478742528a0d31c97dcee939b166a51be858721d40ad5984110893` | CreativeML OpenRAIL-M derivative | Retain the complete terms, attribution, modification notice, and use restrictions |
 | Starting student | `nota-ai/bk-sdm-tiny-2m@aad3e0e8ba61b7cb9f64869dc4e586f8ad9d3665` | Pinned model card declares CreativeML OpenRAIL-M | Derivative-weight obligations apply |
 | Frozen teacher | `CompVis/stable-diffusion-v1-4@133a221b8aa7292a167afc5127cb63fb5005638b` | Pinned model card declares CreativeML OpenRAIL-M | Distillation from outputs and activations retains derivative-weight obligations |
 | Tokenizer and text encoder | Byte-identical components in the two pinned pipelines | CreativeML OpenRAIL-M lineage | Bundled as upstream model components |
@@ -30,9 +30,9 @@ The separately bundled Apache-2.0 project-code license is 9,147 bytes with
 SHA-256
 `e26a0375b714267325c27905ba947fdc41ebc0b7a36940a49ae12379ed6208d6`.
 
-Calling this artifact a research preview does not create a new weight license
-or waive OpenRAIL-M restrictions. Users must review and follow the complete
-terms for copying, redistribution, modification, and use.
+Publishing this artifact as a public release does not create a new weight
+license or waive OpenRAIL-M restrictions. Users must review and follow the
+complete terms for copying, redistribution, modification, and use.
 
 ## Data terms
 
@@ -53,5 +53,4 @@ foundational example behind the upstream teacher.
 
 Pinned model IDs, revisions, and license declarations are evidence of weight
 lineage; they are not substitutes for foundational data provenance. This
-unresolved inherited scope is a principal reason the package remains
-**RESEARCH PREVIEW · PRODUCTION PILOT · NOT RELEASE-READY**.
+inherited scope remains explicitly disclosed with the public release.

README.md

@@ -5,155 +5,44 @@ inference: false
 base_model: nota-ai/bk-sdm-tiny-2m
 license: creativeml-openrail-m
 tags:
+  - clover-image
   - text-to-image
   - diffusion
   - stable-diffusion
   - knowledge-distillation
-  - research-preview
+  - compact
+  - local-inference
 ---
 
-# Clover Image Tiny — Research Preview
+# Clover Image Tiny 🍀
 
-**Clover Image Tiny** is a compact, consumer-runnable text-to-image model with
-a 323,384,964-parameter denoiser and a complete Diffusers package of about
-1.67 GB. It generates locally on Apple silicon, NVIDIA CUDA systems, or CPU;
-no hosted inference API is required. Its examples have the recognizable,
-playful fidelity that can reasonably be described informally as
-**DALL·E mini-ish**. That phrase is a qualitative analogy, not a benchmark or
-claim of equivalent architecture, training scale, or measured quality.
+![Clover Image Tiny mosaic banner](assets/clover-image-tiny-banner.png)
 
-This exact artifact is a conventional knowledge-distillation checkpoint
-released as a research preview. Clover trained the checkpoint for 500 optimizer
-steps on an exact licensed 1,000-pair calibration set, so it is a genuinely
-modified model rather than a rename of unchanged upstream weights. It was
-**not trained from random initialization**: it starts from BK-SDM-Tiny-2M and
-was distilled with a frozen Stable Diffusion v1.4 teacher. Calling it "trained
-from scratch" would therefore be inaccurate. The validated reference recipe
-uses 50-step PNDM, 512×512 output, classifier-free guidance 7.5, and an empty
-negative prompt.
+A compact 512×512 text-to-image model you can run locally on macOS, Windows,
+or Linux.
 
-The checkpoint is a production-data quality-refresh pilot, not a release-ready
-model or a controlled quality benchmark. Its compact size, coherent example
-outputs, exact lineage, and local runner make it useful today for creative
-experimentation and compact-model research.
+**323,384,964 denoiser parameters · about 1.67 GB · 4–100 inference steps ·
+PyTorch/Diffusers**
 
-## Try the live demo
+Clover Image Tiny is the public PyTorch/Diffusers checkpoint release behind
+these examples. Its output has a recognizable, playful
+**DALL·E mini-ish** character. That is a visual description, not a claim of
+equivalent architecture, training scale, or benchmark performance.
 
-[**Open Clover Image Tiny in the public ZeroGPU demo →**](https://huggingface.co/spaces/neonforestmist/Clover-Image-Tiny-Demo)
+[**Try Clover Image Tiny in the live ZeroGPU demo →**](https://huggingface.co/spaces/neonforestmist/Clover-Image-Tiny-Demo)
 
-The hosted demo exposes prompt, negative prompt, seed, guidance, dimensions,
-scheduler, and 4–100 conventional Diffusers inference steps. It generates one
-image per request, defaults to the 50-step PNDM recipe, and keeps the packaged
-safety checker enabled.
-
-## Exact artifact identity
-
-| Field | Value |
-|---|---|
-| Repository | `neonforestmist/Clover-Image-Tiny` |
-| Status | **RESEARCH PREVIEW · PRODUCTION PILOT · NOT RELEASE-READY** |
-| Experiment | `clover-kd-20260712T050925Z-01KXABNHP0` |
-| Training stage | Stage B knowledge distillation |
-| Optimizer step | 500 |
-| Checkpoint SHA-256 | `4a5b99ff18478742528a0d31c97dcee939b166a51be858721d40ad5984110893` |
-| Checkpoint-bundle SHA-256 | `384b6515f5f26838aea33ec9a941e06610a20764f0b8637c8b7b0667bfc0d447` |
-| Resolved-config SHA-256 | `80cf9395d1f587dc0c1d440d9f5b55c55c20703187998509bb306d19d463f597` |
-| Dataset-manifest SHA-256 | `50c1249f1cb0d8d690a9acc451ca10c9432eb5a7f4e26f34acb5462096e72322` |
-| Denoiser parameters | `323,384,964` |
-| Package bytes | `1671502952` |
-| Package files | `30` |
-| Validated Stage B source-package checksums SHA-256 | `d9a28d5fe6f5b675ee1b9db52e6d0493c8d3d357bb824eac590911acbd5c3ebc` |
-| Builder source commit | `6675345aed2734128cfb441c81d65a644332ca59` |
-
-The checkpoint completed 500 optimizer steps, 4,000 microsteps, and 4,000
-sample presentations. All 500 recorded training rows were finite and had a
-nonzero gradient. Those are training-integrity observations, not image-quality
-scores.
-
-## Example gallery
-
-![Eight paired baseline and Clover Image Tiny examples](assets/clover-image-tiny-paired-contact-sheet.png)
-
-Each row uses the same prompt and seed. The **left column is the pinned
-BK-SDM-Tiny-2M baseline; only the right column is this Stage B checkpoint**.
-The gallery was generated on an NVIDIA L4 in bfloat16 with 50 PNDM steps,
-guidance 7.5, an empty negative prompt, and 512×512 output.
-With the pinned Diffusers 0.39.0 scheduler, those 50 requested PNDM steps use
-51 U-Net invocations because PLMS repeats its first retained timestep.
-
-All eight Stage B gallery images were finite, nonblank, nonblack, and returned
-clear from the packaged upstream safety checker in that measured run. This
-small engineering subset is not a general safety or quality evaluation. The
-examples demonstrate recognizable objects, people, animals, landscapes,
-interiors, food, and night scenes. Results are not uniformly better than the
-starting model: the bottle example loses prompt fidelity, hands remain weak,
-and some details change without clear improvement.
+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.
 
 ## Run locally
 
-This is a conventional PyTorch/Diffusers model, so it can run on macOS,
-Windows, or Linux. Use Python 3.11 or 3.12 and allow about 2 GB of free disk
-space for the model itself. Mac MPS is the only local runtime measured for this
-preview; Windows/Linux CUDA and CPU execution are supported by the runner but
-their performance is not claimed here.
-
-### Generation controls
-
-The bundled runner exposes the ordinary Diffusers controls below. Its defaults
-exactly preserve the measured gallery recipe.
-
-| Argument | Accepted values | Default | Effect |
-|---|---|---|---|
-| `--steps` | 4–100 | `50` | Conventional diffusion inference steps; more steps usually take longer |
-| `--guidance-scale` | 0.0–20.0 | `7.5` | Strength of text guidance |
-| `--negative-prompt` | Text, or empty | Empty | Content or traits to discourage |
-| `--width` | 256–768, divisible by 64 | `512` | Output width |
-| `--height` | 256–768, divisible by 64 | `512` | Output height |
-| `--scheduler` | `pndm`, `ddim`, `euler`, `euler-a`, `dpmpp-2m` | `pndm` | Sampling algorithm |
-| `--num-images` | 1–4 | `1` | Images generated in one invocation |
-| `--seed` | 0–(2⁶³−1) | `1337` | Starting deterministic seed |
-
-Only **PNDM + 50 steps + guidance 7.5 + 512×512 + an empty negative
-prompt** is the validated gallery and local-MPS recipe. Other combinations are
-deliberately available for exploration, but no comparative quality or speed
-claim is attached to them. These controls are conventional Diffusers scheduler
-iterations for this checkpoint; selecting four or eight requests that many
-iterations.
+Download once, then generate offline with the bundled runner. Python 3.11 and
+3.12 are supported.
 
-For example, this asks for two 512×512 images using 30 Euler steps, stronger
-guidance, and an explicit negative prompt:
+### macOS — Apple silicon
 
-```bash
-python model/examples/generate.py \
-  --model model \
-  --device auto \
-  --local-files-only \
-  --prompt "a tiny glass greenhouse glowing in a moonlit garden, detailed photography" \
-  --negative-prompt "blurry, distorted, low detail" \
-  --steps 30 \
-  --guidance-scale 8.5 \
-  --scheduler euler \
-  --width 512 \
-  --height 512 \
-  --num-images 2 \
-  --seed 1337 \
-  --output greenhouse.png
-```
-
-For multiple images, the first is saved to the requested output and subsequent
-images use numbered names such as `greenhouse-02.png`. Seeds advance
-consecutively from the requested seed. One `greenhouse.png.json` sidecar records
-the resolved controls and every output filename and seed. The runner refuses to
-overwrite an existing planned image or sidecar. Resolution and batch size
-multiply memory use; reduce `--num-images`, width, or height if a consumer GPU
-runs out of memory.
-
-### macOS Apple silicon — MPS
-
-These commands download a complete local copy, install the pinned runtime in
-an isolated environment, and generate through MPS:
-
-```bash
+~~~bash
 mkdir clover-image-tiny-local
 cd clover-image-tiny-local
 
@@ -169,25 +58,22 @@ python model/examples/generate.py \
   --model model \
   --device mps \
   --local-files-only \
-  --prompt "a compact modern library with arched windows" \
-  --seed 1469 \
+  --prompt "a tiny glass greenhouse glowing in a moonlit garden, detailed photography" \
+  --negative-prompt "blurry, distorted, low detail" \
+  --steps 50 \
+  --guidance-scale 7.5 \
+  --scheduler pndm \
+  --seed 1337 \
   --output clover-image-tiny.png
 
 open clover-image-tiny.png
-```
+~~~
 
-If `python3.12` is not installed but Python 3.11 is, use `python3.11` instead.
-After the first download, `--local-files-only` keeps inference offline. The
-script writes the resolved runtime settings beside the PNG as
-`clover-image-tiny.png.json`. This is the PyTorch/Diffusers model; no Core ML or
-iPhone package is required or included.
+Use `python3.11` instead if that is the installed supported Python.
 
 ### Windows — PowerShell
 
-On Windows, the same runner automatically selects an available NVIDIA CUDA GPU
-and otherwise falls back to CPU:
-
-```powershell
+~~~powershell
 mkdir clover-image-tiny-local
 cd clover-image-tiny-local
 
@@ -203,30 +89,121 @@ python model\examples\generate.py `
   --model model `
   --device auto `
   --local-files-only `
-  --prompt "a compact modern library with arched windows" `
-  --seed 1469 `
+  --prompt "a tiny glass greenhouse glowing in a moonlit garden, detailed photography" `
+  --negative-prompt "blurry, distorted, low detail" `
+  --steps 50 `
+  --guidance-scale 7.5 `
+  --scheduler pndm `
+  --seed 1337 `
   --output clover-image-tiny.png
 
 Invoke-Item .\clover-image-tiny.png
-```
+~~~
 
-Use `py -3.11` if that is the installed supported Python. Check
-`python -c "import torch; print(torch.cuda.is_available())"` after installation;
-`False` means `--device auto` will use CPU. A Windows AMD/DirectML path is not
-included or validated.
+Use `py -3.11` if needed. With `--device auto`, the runner selects an
+available NVIDIA CUDA GPU and otherwise uses CPU.
 
 ### Linux
 
-Use the macOS shell flow with `python3.11` or `python3.12`, and replace
-`--device mps` with `--device auto`. It selects CUDA when PyTorch can see an
-NVIDIA GPU and otherwise uses CPU.
+~~~bash
+mkdir clover-image-tiny-local
+cd clover-image-tiny-local
 
-### Python API
+python3.12 -m venv .venv
+source .venv/bin/activate
+python -m pip install --upgrade pip
+python -m pip install "huggingface-hub==0.36.2"
 
-The equivalent conventional configuration, with automatic CUDA/MPS/CPU
-selection, is:
+hf download "neonforestmist/Clover-Image-Tiny" --local-dir model
+python -m pip install -r model/requirements.txt
+
+python model/examples/generate.py \
+  --model model \
+  --device auto \
+  --local-files-only \
+  --prompt "a tiny glass greenhouse glowing in a moonlit garden, detailed photography" \
+  --negative-prompt "blurry, distorted, low detail" \
+  --steps 50 \
+  --seed 1337 \
+  --output clover-image-tiny.png
+~~~
 
-```python
+`--device auto` selects CUDA when PyTorch can see an NVIDIA GPU and otherwise
+uses CPU. After the first download, `--local-files-only` prevents network
+access during generation.
+
+## Generation controls
+
+The command above is ready to copy. Change these flags to explore the model:
+
+| Flag | Accepted values | Default | What it controls |
+|---|---|---|---|
+| `--prompt` | Non-empty text | Required | What to generate |
+| `--negative-prompt` | Text, or empty | Empty | Details to discourage; the starter commands and live demo use `blurry, distorted, low detail` |
+| `--steps` | 4–100 | `50` | Diffusion iterations; more steps take longer and do not guarantee a better image |
+| `--guidance-scale` | 0.0–20.0 | `7.5` | How strongly the image follows the prompt |
+| `--scheduler` | `pndm`, `ddim`, `euler`, `euler-a`, `dpmpp-2m` | `pndm` | Sampling method |
+| `--width` | 256–768, divisible by 64 | `512` | Output width |
+| `--height` | 256–768, divisible by 64 | `512` | Output height |
+| `--num-images` | 1–4 | `1` | Images generated in one run |
+| `--seed` | 0–(2⁶³−1) | `1337` | Repeatable starting seed |
+| `--device` | `auto`, `cuda`, `mps`, `cpu` | `auto` | Compute backend |
+| `--local-files-only` | Flag | Off | Require an already-downloaded local model |
+
+The reference configuration is 50-step PNDM, guidance 7.5, 512×512, one
+image, seed 1337, and an empty negative prompt. The live demo pre-fills
+`blurry, distorted, low detail`; the local runner leaves the field empty unless
+you pass the flag.
+
+For multiple images, the first uses the requested filename and later images use
+numbered names such as `clover-image-tiny-02.png`. Seeds advance from the
+requested seed. A JSON sidecar beside the first PNG records every resolved
+setting, output filename, seed, checksum, and safety result. Existing planned
+outputs are never overwritten.
+
+Run `python model/examples/generate.py --help` for the complete CLI reference.
+
+## Hardware and operating systems
+
+| System | Automatic backend | Precision | Current evidence |
+|---|---|---|---|
+| 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.
+
+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
+631,341,056 bytes. This is a measured point, not a minimum-RAM claim. No Core
+ML or iPhone package is required or included.
+
+## Example outputs
+
+![Eight paired baseline and Clover Image Tiny examples](assets/clover-image-tiny-paired-contact-sheet.png)
+
+Each row uses the same prompt and seed. The left column is the pinned
+BK-SDM-Tiny-2M starting model; the right column is Clover Image Tiny. The
+gallery used an NVIDIA L4 in bfloat16, 50 PNDM steps, guidance 7.5, an empty
+negative prompt, and 512×512 output. With Diffusers 0.39.0, 50 requested PNDM
+steps use 51 U-Net calls because PLMS repeats its first retained timestep.
+
+All eight Clover images were finite, nonblank, nonblack, and cleared by the
+packaged upstream safety checker in this run. The set covers objects, a person,
+an animal, a landscape, an interior, food, a product, and a night scene.
+
+The local MPS reference below used “a compact modern library with arched
+windows,” seed 1469, and the same 50-step configuration:
+
+![Clover Image Tiny local MPS library example](assets/clover-image-tiny-local-mps-library-seed-1469.png)
+
+## Python API
+
+~~~python
 import torch
 from diffusers import DiffusionPipeline, PNDMScheduler
 
@@ -237,121 +214,123 @@ elif torch.backends.mps.is_available():
     device = "mps"
 else:
     device = "cpu"
-dtype = torch.float16 if device in {"cuda", "mps"} else torch.float32
 
+dtype = torch.float16 if device in {"cuda", "mps"} else torch.float32
 pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=dtype)
 pipe.scheduler = PNDMScheduler.from_config(pipe.scheduler.config)
 pipe = pipe.to(device)
 
 generator_device = "cuda" if device == "cuda" else "cpu"
 generator = torch.Generator(device=generator_device).manual_seed(1337)
-result = pipe(
+image = pipe(
     prompt="a tiny greenhouse glowing in a moonlit garden",
-    negative_prompt="",
+    negative_prompt="blurry, distorted, low detail",
     num_inference_steps=50,
     guidance_scale=7.5,
     height=512,
     width=512,
     generator=generator,
-)
-result.images[0].save("clover-image-tiny.png")
-```
-
-The bundled `examples/generate.py` chooses CUDA, MPS, or CPU safely and writes
-the resolved settings next to the PNG:
-
-```bash
-python examples/generate.py \
-  --model "neonforestmist/Clover-Image-Tiny" \
-  --prompt "a tiny greenhouse glowing in a moonlit garden" \
-  --output clover-image-tiny.png
-```
-
-Run `python examples/generate.py --help` for the complete control reference and
-accepted ranges.
-
-Seeded generation is repeatable only within the limits of the selected runtime.
-Different devices, dtypes, kernels, and dependency builds can produce different
-pixels. The bundled Mac example below was measured locally on an Apple M4 Pro
-with MPS and fp16: 18.21 seconds, exactly 51 U-Net calls, and 631,341,056 bytes
-of process-lifetime maximum RSS. It used the prompt “a compact modern library
-with arched windows” and seed 1469. The packaged safety checker ran and returned
-clear. This does not promise identical pixels or performance on another Mac.
-
-![Clover Image Tiny local MPS library example](assets/clover-image-tiny-local-mps-library-seed-1469.png)
-
-Its machine-readable evidence is bundled at
-`evidence/clover-image-tiny-local-mps-library-seed-1469.json`; the image
-SHA-256 is
-`f8830346f2a9c2b9a8c2a01d8f90e6925c93d667c1bcf998aa904a150589a742`.
-
-## Training lineage
-
-- Starting student:
-  `nota-ai/bk-sdm-tiny-2m@aad3e0e8ba61b7cb9f64869dc4e586f8ad9d3665`
-- Frozen teacher:
-  `CompVis/stable-diffusion-v1-4@133a221b8aa7292a167afc5127cb63fb5005638b`
-- Fine-tuning data: exactly 1,000 accepted image-caption pairs from
+).images[0]
+image.save("clover-image-tiny.png")
+~~~
+
+Seeded generation is repeatable within the selected runtime. Different
+devices, dtypes, kernels, and dependency builds can produce different pixels.
+
+## About this release
+
+Clover Image Tiny is a conventional knowledge-distillation checkpoint trained
+for 500 optimizer steps on an exact licensed 1,000-pair calibration set. The
+run recorded 4,000 microsteps and 4,000 sample presentations, with finite
+training rows and nonzero gradients throughout.
+
+The model was initialized from
+`nota-ai/bk-sdm-tiny-2m@aad3e0e8ba61b7cb9f64869dc4e586f8ad9d3665`
+and distilled with a frozen
+`CompVis/stable-diffusion-v1-4@133a221b8aa7292a167afc5127cb63fb5005638b`
+teacher. It is a genuinely modified checkpoint, but it was not trained from
+random initialization.
+
+This checkpoint release covers the conventional PyTorch/Diffusers model shown
+here. Formal quality acceptance, the separate 1–4 Leaf architecture, Core ML,
+and iPhone work remain separate workstreams and are not claims of this package.
+
+## Quality and known behavior
+
+- The included gallery demonstrates recognizable subjects across colorful
+  scenes, products, food, an animal, a landscape, and an interior.
+- Individual results vary by prompt, seed, scheduler, and step count. More
+  steps increase runtime but do not guarantee a better result.
+- Hands, anatomy, exact counts and relationships, and readable text can be
+  difficult.
+- The paired eight-prompt gallery is a reproducible engineering sample, not a
+  controlled benchmark or broad human-preference study.
+- Resolution and batch size multiply memory use.
+
+## Safety
+
+The upstream safety checker is packaged and enabled in both the supported
+runner and hosted demo. A flagged output may be returned as a black placeholder;
+the JSON sidecar records `nsfw_content_detected` so the result is not silent.
+The checker is useful but not a complete moderation system and can miss harmful
+content or over-filter benign content.
+
+Applications should add controls appropriate to their audience and review
+outputs before sharing them. Do not use the model for consequential decisions,
+identity claims, medical or legal conclusions, harassment, exploitation,
+illegal activity, or uses prohibited by CreativeML OpenRAIL-M.
+
+## Training lineage and data
+
+- Clover fine-tuning data: exactly 1,000 accepted image-caption pairs from
   `Spawning/PD3M@2a5eb24a8dccf245acd8e56341761aee06da0bdf`
-- Split: 973 train, 17 validation, and 10 test records in one checksummed shard
+- Split: 973 train, 17 validation, and 10 test records
 - Data gate: `CDLA-Permissive-2.0`; accepted items retain CC0-1.0 or Public
   Domain Mark 1.0 provenance
 - Preprocessing: deterministic center crop and 512×512 JPEG conversion,
   version `clover-pd3m-center-crop-512-jpeg95-v1`
+- Dataset-manifest SHA-256:
+  `50c1249f1cb0d8d690a9acc451ca10c9432eb5a7f4e26f34acb5462096e72322`
 
-The 1,000 records describe only this Clover fine-tuning run. The starting
-student and teacher already contain knowledge learned from much larger upstream
-corpora. Their pinned model cards and weight licenses were verified, but the
-project does not have complete per-record provenance for all foundational
-pretraining behind those weights. In particular, the BK-SDM model card names
-LAION-Aesthetics V2 6.25+ and 2,256,472 pairs without the per-record evidence
-required by Clover's full release policy. This inherited gap is a material
-reason the package is labeled a research preview and not release-ready.
-
-See `DATA_PROVENANCE.md`, `MODEL_DATA_LICENSES.md`, the bundled CreativeML Open
-RAIL-M terms, and the package checksums for the portable evidence included here.
-
-## Intended use
-
-- Research and inspection of compact Stable Diffusion knowledge distillation
-- Reproducing the fixed conventional 50-step engineering examples
-- Exploring step count, guidance, negative prompting, resolution, schedulers,
-  and small batches through the bundled local runner
-- Comparing this early calibration checkpoint with its pinned starting student
-- Non-consequential creative experimentation subject to the model license
-
-## Limitations
-
-- The model was fine-tuned for only 500 optimizer steps on 1,000 pairs.
-- The eight-prompt gallery is an engineering-health subset, not a representative
-  quality, alignment, diversity, bias, or human-preference evaluation.
-- Results may omit requested objects, lose relationships or counts, produce
-  malformed anatomy and hands, render text poorly, or preserve/amplify biases
-  from upstream models and data.
-- The Stage B changes are modest and can make individual prompts worse.
-- The included pipeline is the conventional PyTorch/Diffusers path only.
-
-## Safety and out-of-scope use
-
-The upstream safety checker is included and was exercised in the recorded
-gallery run, but it is not a complete safety system and can miss harmful output
-or over-filter benign output. Applications should add appropriate prompt and
-output controls, human review, and policy enforcement.
-
-The bundled runner keeps that checker enabled and does not expose a bypass
-flag. A flagged result may be returned as a black placeholder; its sidecar sets
-`nsfw_content_detected` for the corresponding image so the condition is not
-silent. Developers integrating the raw Diffusers pipeline are responsible for
-providing an appropriate moderation system for their application.
-
-Do not use this preview for consequential decisions, identity claims, medical
-or legal conclusions, harassment, exploitation, illegal activity, or any use
-prohibited by CreativeML OpenRAIL-M. Review outputs before sharing them.
+The 1,000 records describe the Clover fine-tuning run. The student and teacher
+already contain knowledge from larger upstream corpora. Their pinned model
+cards and weight licenses are disclosed, while complete item-level provenance
+for all foundational pretraining is not available to this project.
+
+See `DATA_PROVENANCE.md` for the portable manifest identity and
+`MODEL_DATA_LICENSES.md` for the complete component ledger.
 
 ## Licenses
 
-The model weights are a derivative under **CreativeML OpenRAIL-M**. The small
-example and packaging code is licensed separately under **Apache-2.0**. The
-PD3M dataset declaration and each accepted item's public-domain status remain
-separate from both licenses. Read the bundled license files and
-`MODEL_DATA_LICENSES.md`; this summary is not legal advice.
+The model weights are a derivative under **CreativeML OpenRAIL-M**. The example
+runner and packaging code are under **Apache-2.0**. Dataset and item-level terms
+remain separate. Read `LICENSE`, `LICENSE-MODEL-CREATIVEML-OPENRAIL-M.txt`,
+`LICENSE-CODE`, and `MODEL_DATA_LICENSES.md` before redistribution or use.
+
+The hero mosaic is user-supplied presentation artwork included by explicit
+request for display in this public model repository. It is not benchmark
+evidence, its panel-generation provenance is not claimed, and this package
+does not grant a downstream reuse license for it.
+
+## Reproducibility and artifact identity
+
+| Field | Value |
+|---|---|
+| Repository | `neonforestmist/Clover-Image-Tiny` |
+| Release status | **PUBLIC PYTORCH/DIFFUSERS CHECKPOINT RELEASE** |
+| Training experiment | `clover-kd-20260712T050925Z-01KXABNHP0` |
+| Optimizer step | 500 |
+| Checkpoint SHA-256 | `4a5b99ff18478742528a0d31c97dcee939b166a51be858721d40ad5984110893` |
+| Checkpoint-bundle SHA-256 | `384b6515f5f26838aea33ec9a941e06610a20764f0b8637c8b7b0667bfc0d447` |
+| Resolved-config SHA-256 | `80cf9395d1f587dc0c1d440d9f5b55c55c20703187998509bb306d19d463f597` |
+| Denoiser parameters | `323,384,964` |
+| Package bytes | `1676086612` |
+| Package files | `31` |
+| 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

@@ -1,19 +1,20 @@
 {
-  "DATA_PROVENANCE.md": "1be188980913e7b68490228ed17878f4cb0d9e6f30ab0c8485864da80d18a591",
+  "DATA_PROVENANCE.md": "d0be84c8412aa9766c2477e145c3c4e9c7ff5beaf8116de5acc8d05e6616f857",
   "LICENSE": "be351ebe7ac01bcdbb018639aadcfd38f136b7dc3f2a3d4d3a24db51d1b210ef",
   "LICENSE-CODE": "e26a0375b714267325c27905ba947fdc41ebc0b7a36940a49ae12379ed6208d6",
   "LICENSE-MODEL-CREATIVEML-OPENRAIL-M.txt": "be351ebe7ac01bcdbb018639aadcfd38f136b7dc3f2a3d4d3a24db51d1b210ef",
-  "MODEL_DATA_LICENSES.md": "8f6b712826f9904561fb32038635612722be61cfd776da58fb61a4848a03148e",
-  "README.md": "880346a5eb2d7f1726c215d1214853f5938a3adb80645537236456b22af5c797",
+  "MODEL_DATA_LICENSES.md": "39501a1246aff094fcc987a548f7e8bd750dd21900b43c5a2e8cbcab305bb0b1",
+  "README.md": "beb79bcda817f6af19a70fd2fcb11657cd456fa4b3a83fdaafad3330d3cf18d7",
+  "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": "fcea598655f7e144bc1ccce9be6d4e9e166915a3ad3c26fc0aa6c8ade00b49f1",
+  "examples/generate.py": "4cfba0d6f3f2a5a9d1090564be5b618d06b757ef258ec7cfcff0523353e1466b",
   "feature_extractor/preprocessor_config.json": "205d45875859846dc1ca211b9a19f5db72f47e953b396954ee34d48d8e95c3c6",
   "model_index.json": "792073e269e5caff40b3f8c553387540c17a5d900ed0e9cbfab309d650e708dd",
   "requirements.txt": "9dbb74869a34e3b610f737bce8a9d2a20691fd0fa416cf6bb42354b78e0a3861",
-  "research_preview.json": "bbc4ccd5811a976f1178588d4e3bf7ab64fdba04d84e3f1a1569bd622146ca2b",
+  "research_preview.json": "3ee097bdf9ab47f7897df545bb91096ed054a874adaab7310d32b1968496d032",
   "safety_checker/config.json": "241bd8fb1ba6feff0d7421f7af0f85743711c5d76353626f71f7e2cc8009ac7c",
   "safety_checker/model.safetensors": "57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6",
   "scheduler/scheduler_config.json": "184bc33ed887951dd86e37f20c878710c4e18e1c5fd4461256a3825679b53d15",

examples/generate.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Generate configurable conventional Clover Image Tiny preview images."""
+"""Generate images with the Clover Image Tiny public release."""
 
 from __future__ import annotations
 
@@ -63,7 +63,7 @@ def _parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         description=(
             "Run Clover Image Tiny with configurable conventional Diffusers settings. "
-            "The defaults reproduce the validated 50-step preview recipe."
+            "The defaults reproduce the validated 50-step reference recipe."
         )
     )
     parser.add_argument("--model", required=True, help="Hub repository ID or local directory")
@@ -246,7 +246,7 @@ def main() -> int:
         "validated_gallery_recipe": validated_gallery_recipe,
         "leaf_steps": None,
         "cross_device_pixel_identity_claimed": False,
-        "usage_label": "RESEARCH PREVIEW - PRODUCTION PILOT - NOT RELEASE-READY",
+        "usage_label": "CLOVER IMAGE TINY - PUBLIC CHECKPOINT RELEASE",
     }
     for output_path, payload in zip(output_paths, image_payloads, strict=True):
         _write_new(output_path, payload)

research_preview.json

@@ -1,6 +1,6 @@
 {
   "build": {
-    "repository_commit": "6675345aed2734128cfb441c81d65a644332ca59",
+    "repository_commit": "9f5ce495fcb88238ec7fdc33204fa42ec9690c37",
     "sources": {
       "LICENSE-CODE": {
         "sha256": "e26a0375b714267325c27905ba947fdc41ebc0b7a36940a49ae12379ed6208d6",
@@ -19,19 +19,23 @@
         "tracked_at_commit": true
       },
       "hf/stage_b_preview/DATA_PROVENANCE.md": {
-        "sha256": "1be188980913e7b68490228ed17878f4cb0d9e6f30ab0c8485864da80d18a591",
+        "sha256": "d0be84c8412aa9766c2477e145c3c4e9c7ff5beaf8116de5acc8d05e6616f857",
         "tracked_at_commit": true
       },
       "hf/stage_b_preview/MODEL_DATA_LICENSES.md": {
-        "sha256": "8f6b712826f9904561fb32038635612722be61cfd776da58fb61a4848a03148e",
+        "sha256": "39501a1246aff094fcc987a548f7e8bd750dd21900b43c5a2e8cbcab305bb0b1",
         "tracked_at_commit": true
       },
       "hf/stage_b_preview/README.template.md": {
-        "sha256": "f2a571eec6d039a52b27dbab2b354ceeda3f7b92c4fa0ab70b42636eb65fbfc5",
+        "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": "fcea598655f7e144bc1ccce9be6d4e9e166915a3ad3c26fc0aa6c8ade00b49f1",
+        "sha256": "4cfba0d6f3f2a5a9d1090564be5b618d06b757ef258ec7cfcff0523353e1466b",
         "tracked_at_commit": true
       },
       "hf/stage_b_preview/requirements.txt": {
@@ -59,7 +63,7 @@
         "tracked_at_commit": true
       },
       "src/clover_image/stage_b_preview.py": {
-        "sha256": "c7448cc70c771ecd0501eae803a01a6d7ea8dd12958a8922503a9d4d01e7ed5c",
+        "sha256": "7a769e4e6098580c4235c56ff29ab3cc17496d5b6d528be425ee8000cc86e849",
         "tracked_at_commit": true
       }
     }
@@ -116,7 +120,24 @@
     "human_review": "not_measured",
     "quality_evaluation": "not_measured"
   },
-  "metadata_sha256": "fc6c8420017ca2ca0c0774d0d47ca5d9769e05a4b4eea1e6e9408d3039572391",
+  "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,
@@ -128,7 +149,7 @@
     "scheduler": "PNDMScheduler",
     "width": 512
   },
-  "schema_version": 1,
+  "schema_version": 2,
   "source_package": {
     "checksums_path": "evidence/stage-b-inference-checksums.json",
     "checksums_sha256": "d9a28d5fe6f5b675ee1b9db52e6d0493c8d3d357bb824eac590911acbd5c3ebc",