InclusionAIImage modelOpen weights

Ming-Image-0.1-Design-Layer

PopularityRank 466 of 875

30out of 100+1 vs. last month

Summary

Ming-Image-0.1-Design-Layer takes a flattened design and a layer plan, then decomposes it into requested RGBA layers, unlike Ming-Image-0.1-Design. The recommended working resolution is 1024, or 512 for faster runs.

Its separate MIT checkpoint saves outputs as individual RGBA PNG files while preserving the input aspect ratio. Ming-Image-0.1-Design-Layer is therefore a decomposition model, not a second image-generation variant.

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 12 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

Crello RGB L1 error (MLM 0) (Show measurement, test conditions, and source)

Source value: 0.0574
Score: 0.0574
Metric: RGB L1 error
Unit: No unit provided
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Lower is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=0.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count or RGB L1 units/normalization.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello RGB L1 error (MLM 1) (Show measurement, test conditions, and source)

Source value: 0.0359
Score: 0.0359
Metric: RGB L1 error
Unit: No unit provided
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Lower is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=1.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count or RGB L1 units/normalization.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello RGB L1 error (MLM 2) (Show measurement, test conditions, and source)

Source value: 0.0343
Score: 0.0343
Metric: RGB L1 error
Unit: No unit provided
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Lower is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=2.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count or RGB L1 units/normalization.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello RGB L1 error (MLM 3) (Show measurement, test conditions, and source)

Source value: 0.032
Score: 0.032
Metric: RGB L1 error
Unit: No unit provided
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Lower is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=3.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count or RGB L1 units/normalization.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello RGB L1 error (MLM 4) (Show measurement, test conditions, and source)

Source value: 0.0317
Score: 0.0317
Metric: RGB L1 error
Unit: No unit provided
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Lower is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=4.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count or RGB L1 units/normalization.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello RGB L1 error (MLM 5) (Show measurement, test conditions, and source)

Source value: 0.0314
Score: 0.0314
Metric: RGB L1 error
Unit: No unit provided
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Lower is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=5.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count or RGB L1 units/normalization.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello Alpha soft IoU (MLM 0) (Show measurement, test conditions, and source)

Source value: 0.8923
Score: 0.8923
Metric: Alpha soft IoU
Unit: ratio
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Higher is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=0.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello Alpha soft IoU (MLM 1) (Show measurement, test conditions, and source)

Source value: 0.9288
Score: 0.9288
Metric: Alpha soft IoU
Unit: ratio
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Higher is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=1.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello Alpha soft IoU (MLM 2) (Show measurement, test conditions, and source)

Source value: 0.9362
Score: 0.9362
Metric: Alpha soft IoU
Unit: ratio
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Higher is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=2.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello Alpha soft IoU (MLM 3) (Show measurement, test conditions, and source)

Source value: 0.9406
Score: 0.9406
Metric: Alpha soft IoU
Unit: ratio
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Higher is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=3.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello Alpha soft IoU (MLM 4) (Show measurement, test conditions, and source)

Source value: 0.9416
Score: 0.9416
Metric: Alpha soft IoU
Unit: ratio
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Higher is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=4.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Crello Alpha soft IoU (MLM 5) (Show measurement, test conditions, and source)

Source value: 0.9424
Score: 0.9424
Metric: Alpha soft IoU
Unit: ratio
Benchmark version: Crello test set, official model-card Table 1
Category: image-layer-decomposition
Direction: Higher is better
Source type: vendor-reported
Evaluator: inclusionAI Ming-Image-0.1-Design-Layer model-card figure
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Crello test set; official-card result row CLEAR-1024 (Ours); max-allowed layer merge (MLM)=5.
Context: The figure is embedded on the official card for this exact model, but labels the result row CLEAR-1024 (Ours) rather than printing the checkpoint ID in-row. It does not state a sample count.

Source inclusionAI Ming-Image-0.1-Design-Layer model-card figure

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

The 100 most popular models of this category, 0 to 100, higher is more popular

20 of 100 models

Stable Diffusion XL 1.072

Anima Base v1.068

SDXL Turbo63

Stable Diffusion Turbo63

PixArt-Sigma-XL-2-1024-MS44

Janus-Pro-7B44

HunyuanImage 3.0 Instruct44

MOSS-Image-Base44

Ming-Image-0.1-Design-Layer30

Stable Diffusion XL 1.0

Anima Base v1.0

SDXL Turbo

Stable Diffusion Turbo

PixArt-Sigma-XL-2-1024-MS

Janus-Pro-7B

HunyuanImage 3.0 Instruct

MOSS-Image-Base

Ming-Image-0.1-Design-Layer

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 5, 2026

Ming-Image-0.1-Design-LayerKrea 2 LargeNano Banana 2 LiteHiDream-O1-Image-1.5Grok Imagine Image Quality

All specifications

Architecture

Model class: Image-to-image model for layer decomposition; Source: Model class

Input and output

Input: Image and layer plan or requested layer count; Source: Input
Output: Separate RGBA PNG files per layer; Source: Output

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking: Unknown; no source
Watermarking technique: Not known; no source

Licence and access

License: MIT; Source: License

API

Model ID: inclusionAI/Ming-Image-0.1-Design-Layer; Source: Model ID

Further details

Working resolution: 1024 recommended, 512 for faster runs, aspect ratio is preserved; Source: Working resolution
Hardware: One CUDA GPU with 80 GiB VRAM in the validated configuration; Source: Hardware

Sources and data date

Show all 9 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.

Type	Evidence and data date
Research status	Research date October 4, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Additional source	Ming-Image repository (retrieved October 3, 2026) · Ming-Image repository · Editorial description reviewed October 3, 2026
Additional source	Ming-Image Design Layer model card (retrieved October 3, 2026; October 15, 2026) · Ming-Image Design Layer model card · Editorial description reviewed October 3, 2026
Additional source	inclusionAI Ming-Image-0.1-Design-Layer model-card figure (retrieved October 15, 2026)
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0