alt.freeweights.text / Ming-Image-0.1-Design-Layer

From: inclusionAI <huggingface.co/inclusionAI>Newsgroups: alt.freeweights.textSubject:

Ming-Image-0.1-Design-Layer

Date: 2026-11-15Commit: ff1b22dSigned: 2DC28CC7B26A283B ✓

Image text to image model with 6.2B parameters. Safetensors weights, 65.2 GB in all. Published by inclusionAI under MIT.

6.2B params65.2GBMing-Image-0.1-Design-Layersafetensorspermissive

FactsParams6.2BSize65.2 GBFormatssafetensorsTaskimage text to imageLicenseMITFrom sourcepermissive

$ fw get inclusionAI/Ming-Image-0.1-Design-Layer
# manifest sha256 be12eef8c551… · 65.2 GB · 41 files
$ fw verify ./Ming-Image-0.1-Design-Layer inclusionAI/Ming-Image-0.1-Design-Layer

From sourceHosted (signed)inclusionAI/Ming-Image-0.1-Design-LayerLast check: 2026-11-15 03:49 UTC

Run at home Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Run8 Fine-tune7 Convert8 Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

Transformers LocalAI tinygrad Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Overview

Size: 65.2 GB
Weights: 65.2 GB (safetensors)
Parameters: 6.2B
Formats: safetensors
Task: image text to image
License: MIT (permissive)
Files: 41, each with a sha256
Publisher: inclusionAI
Added: 2026-11-15
Section: alt.freeweights.text

Lineage

Original release from the publisher.

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 03:49 UTC	passed

Model card

From the publisher at commit ff1b22d. Shown as plain text with links; images open at the publisher.

Ming-Image-0.1-Design-Layer#

🧩 ModelScope · 🤗 Hugging Face · 📄 Blog · 🖥️ Demo

🎨 Design Skill · 📊 PPT Skill

Ming-Image-0.1-Design-Layer decomposes a flattened design image into a requested number of RGBA layers using an image and a layer plan.

Quick Start#

Use the companion Ming-Image repository for installation and inference:

git clone https://github.com/inclusionAI/Ming-Image
cd Ming-Image
pip install -r requirements.txt

python infer.py \
  --model inclusionAI/Ming-Image-0.1-Design-Layer \
  --task layer-decompose \
  --input-image assets/layer_samples/card_making_input.png \
  --prompt assets/layer_samples/card_making_prompt.txt \
  --attn-implementation flash_attention_2 \
  --resolution 1024 \
  --output-dir outputs/layers

This runs the released six-layer card-making example. See the full layer-decomposition demo for the output structure and layer-count behavior.

Prompt enhancement (PE) can use Ling-3.0-flash-VL or qwen3.8-27B; see layer-decomposition prompt rewriting.

Deployment#

We recommend the following inference frameworks to serve the model:

vLLM-Omni: see the recipes and installation guide.

Recommended settings#

Working-resolution bucket: 1024 (recommended), or 512 for faster layer decomposition. The output preserves the input image's aspect ratio.
Sampling steps: 12.
CFG scale: 2.0.
Precision: BF16.
Hardware: one CUDA GPU with 80 GiB VRAM (validated configuration).

Provide --input-image plus either a detailed layer specification through --prompt, or omit --prompt and set --num-layers N to create the default request. When --prompt is supplied, the layer count declared in that prompt controls the output count. The standalone outputs are saved as RGBA PNG files.

Gallery#

Image: Ming-Image-0.1-Design-Layer decomposition example

The example shows the input design, six decomposed layers, and the recomposed result.

Image: Ming-Image-0.1-Design-Layer gallery

The gallery shows additional flattened designs, their transparent layers, and the corresponding recomposed results.

Performance#

Image: Layer-decomposition results on the Crello test set

The table reports quantitative layer-decomposition results on the Crello test set; lower RGB L1 and higher Alpha soft IoU are better.

License#

This model is released under the MIT License.

Files

41 files · 65.2 GBWeights 65.2 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 41 files with their sha256

File	Size	sha256
.gitattributes	1.75 KB	f27ea6c46e75592d54094613a9be3517528c2c60b1fe83b2dfbcfc0cddad9554
LICENSE	1.07 KB	b772c54f1f150a680e7c083a92431c518cf62821a407f6cccdf53f6a07bcf702
README.md	3.66 KB	5220c37c6955ab7bd0f84fb83ca330ffa189881dbf9aeb962341a280f240371b
assets/gallery.webp	3.71 MB	6bb8100d73e84137990da6fe84d6336fd1f425c3e95a7963f0783f6cefc38417
assets/performance.webp	105 KB	b5a14d246ba3e1f3f9e22aa19a429094408e17f3f8e2b34330ef56b19b5ffa8a
assets/showcase.webp	807 KB	a5e243217323e4233e6c7fd427814794739e0d3de44b0dbdcb1c55ca00399c1b
config.json	5.56 KB	f797c39adcd1624e5bfc94f60d2a86095dc40978f8cf230fcd11ada877c597ea
connector/config.json	1.31 KB	d77f626989d10af81a3293735c1a4d1885ca2f8d72d88cfd05481113187bbc51
connector/generation_config.json	242 B	cd5866254bd02b52464b75af06818afa882298a64d30a3819343a4fa4ed16ca9
connector/model-00001-of-00002.safetensors	5.00 GB	efe1467052e70b4aa9b6fd4bdaead80b6e9c18d7b51fbeba542243c26b456f3d
connector/model-00002-of-00002.safetensors	1.18 GB	239915774bb4d79ef8690b97ee7a631c70852208448f9ffc48962fceffc97d37
connector/model.safetensors.index.json	27.7 KB	f004b386e07101ea27aebc7eda98f92a88e41c45fa8f51fc49edcb12d6fd199f
mllm/config.json	5.56 KB	f797c39adcd1624e5bfc94f60d2a86095dc40978f8cf230fcd11ada877c597ea
mllm/model-00001-of-00007.safetensors	5.00 GB	7cf3d5e41fb13a949e86608409ca1189750aa707c1d15629be96230d676547fb
mllm/model-00002-of-00007.safetensors	5.00 GB	5680a7125f2fe651477965aaa2b6915b86a1c7a29290c352de0aa3b3a024d8af
mllm/model-00003-of-00007.safetensors	5.00 GB	98b2769083e814bdf1fdb70005ac3283319c13a8e0d0e0f9aceb610e3072550c
mllm/model-00004-of-00007.safetensors	5.00 GB	aa782d99765ec843e1ea9760b6f0b274a66a36c761b7de9ee36a1e32485df19d
mllm/model-00005-of-00007.safetensors	5.00 GB	92210b0acbca03b224498f8e1bad0fc17ed1898f38cfc5fead5247cb2bcdc3e3
mllm/model-00006-of-00007.safetensors	5.00 GB	66c4092e8235aabbfc44ff230bce613f7e31a75f0b14fe7a6532e05889d5dd31
mllm/model-00007-of-00007.safetensors	4.01 GB	139c1952cde5680460d02eb1a8ad8d96273f0472afff0460bb39cbbeb43b4692
mllm/model.safetensors.index.json	1.46 MB	ed43fe42536f78c6178a134db1a83f5f424cb3e39f188699b527055c3288a773
mllm/preprocessor_config.json	450 B	e63066dde0329df1642c8dd9a269d613307804084d12e0787ccc887839339091
mllm/special_tokens_map.json	879 B	8c383d444e75b12f2643b4695bece7f3dd1d43725d8a26deeb019aa40a8f891d
mllm/tokenizer.json	12.2 MB	e4f5fe09e7484071da5fa93cfb82f7db15c0ebf9b6ee9821599c5a997563ee96
mllm/tokenizer_config.json	58.8 KB	861c20bea04c2057362f226658ad9209978ff294b8a95591a0d32f69dbd3fc28
mlp/config.json	330 B	682c34c6c39173b396aa24f444098e495c7b731247d935552dc7d6714154adce
mlp/model.safetensors	125 MB	2ec9b54aa1279b2747b9241cc682c2376f4d94b539cd8d07b71da660fd18b8f7
scheduler/scheduler_config.json	173 B	79bd98cddf1a60d365f3072d713ffad832239f57c837bba0e9da3cff40bfafc5
transformer/config.json	584 B	e3851ddff548a845cb94b99b4889070e845ac47787f3b3a0c54b70a374aeba17
transformer/diffusion_pytorch_model-00001-of-00009.safetensors	2.97 GB	f96621e3e8f640ac978a91c8ac251998ea7e0ebfb9c67ce9166d26f1121f0161
transformer/diffusion_pytorch_model-00002-of-00009.safetensors	2.95 GB	090c2f2d09710fefd23d0ed1bef4ff3a63d945ab3a7c1ae0ab3e7c11c9baf7d1
transformer/diffusion_pytorch_model-00003-of-00009.safetensors	2.95 GB	08b20b84ca1ac87197d942dbf8396593d7d624c99d0bc4bb4951c379ab931e7c
transformer/diffusion_pytorch_model-00004-of-00009.safetensors	2.95 GB	370dd46b4aaf4abcf0c9fd4a7c311dacafc8d2910b1309f093ee529dd21e702f
transformer/diffusion_pytorch_model-00005-of-00009.safetensors	2.89 GB	c6920bb07e55e8ddb4aeced3bd6fe1e0aff6fc04758fe140d22ac2c3826eec62
transformer/diffusion_pytorch_model-00006-of-00009.safetensors	2.89 GB	5f6d4f469d18eb224e467eaf0e566b8a8816d69d64f89e51c6b1f41234d17cf4
transformer/diffusion_pytorch_model-00007-of-00009.safetensors	2.89 GB	cf012dbc6e119859999acb484189ac25aabb849365dd882c86fc626e51914736
transformer/diffusion_pytorch_model-00008-of-00009.safetensors	2.89 GB	ed36c18f7ef6a479f393f32bfbb51d292211a3a7a8369eae5c8c167138ea3e09
transformer/diffusion_pytorch_model-00009-of-00009.safetensors	1.21 GB	91a5e0868f70e063282263ceb8b0b2ac210d1b8f0ca5bf05e2d47fbfa8ce35bc
transformer/diffusion_pytorch_model.safetensors.index.json	49.0 KB	ea67bb11167bb94124d2d3fc357716299c5a79dc57fc5fc4d0f13c240ac243f5
vae/config.json	411 B	8db67ee46bb5810ed819d698a8acfc95936d157fe68b66c9ed16b2d5ea04413e
vae/diffusion_pytorch_model.safetensors	254 MB	06520463778e64dca1039c7447890065ee220bc408d15412182e5c3e06f304f1

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
ff1b22d2bd pinned now	2026-11-15 03:49 UTC	41 files · 65.2 GB

Use it

$ fw get inclusionAI/Ming-Image-0.1-Design-Layer
# manifest sha256 be12eef8c551… · 65.2 GB · 41 files
$ fw verify ./Ming-Image-0.1-Design-Layer inclusionAI/Ming-Image-0.1-Design-Layer

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/inclusionAI/Ming-Image-0.1-Design-Layer.json --dir ./Ming-Image-0.1-Design-Layer
$ python3 fw.py verify ./Ming-Image-0.1-Design-Layer ./inclusionAI__Ming-Image-0.1-Design-Layer.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download inclusionAI/Ming-Image-0.1-Design-Layer --revision ff1b22d2bdd0ae6597c0024a42cac7923b24cf92 --local-dir ./Ming-Image-0.1-Design-Layer

Packaged for ComfyUI. Most image, video and music models run in ComfyUI . Check the publisher's page for the workflow. Freeweights does not host it.

Run at home

License

Name: MIT License
Id: MIT
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: License as declared by the publisher. No person read it. 2026-11-15
Text in: LICENSE
Text sha256: b772c54f1f150a680e7c083a92431c518cf62821a407f6cccdf53f6a07bcf702
Terms gate: No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: inclusionAI <huggingface.co/inclusionAI>Newsgroups: alt.freeweights.textSubject: Ming-Image-0.1-Design-LayerDate: 2026-11-15Commit: ff1b22dSigned: 2DC28CC7B26A283B ✓

Upstream: inclusionAI/Ming-Image-0.1-Design-Layer
Pinned commit: ff1b22d2bdd0ae6597c0024a42cac7923b24cf92
Manifest: Ming-Image-0.1-Design-Layer.json · .minisig
Manifest sha256: be12eef8c551e830ca6d5c546eddda708722a7d43b59f12b222245b3d5ae1ba7
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 03:49 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/inclusionAI/Ming-Image-0.1-Design-Layer.json
$ curl -O https://freeweights.allternit.com/manifests/inclusionAI/Ming-Image-0.1-Design-Layer.json.minisig
$ minisign -Vm Ming-Image-0.1-Design-Layer.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download inclusionAI/Ming-Image-0.1-Design-Layer

Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest

minisign, key 2DC28CC7B26A283B. Ming-Image-0.1-Design-Layer.json. Provenance. Takedown history: none.

Source

huggingface.co/inclusionAI/Ming-Image-0.1-Design-Layer

Related models

All of alt.freeweights.text →

From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B

Ming-Image-0.1-Design-Layer

Works with

Runs with

Fine-tune with

Convert with

Scan with

Overview

Model card

Ming-Image-0.1-Design-Layer#

Quick Start#

Deployment#

Recommended settings#

Gallery#

Performance#

License#

Files

Use it

License

Provenance

How to verify

Model tree

Related models