We present WeLM-Image, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis. Designed for single-GPU deployment in WeChat's large-scale consumer applications, the model processes text, reference images, and target latents as one interleaved sequence. A Mixture-of-Transformers (MoT) backbone combines shared attention with independent understanding and generation parameters to limit optimization interference. Equipping each path with Mixture-of-Experts (MoE) modules provides sparse capacity, with 31.7B stored parameters and approximately 5.4B generation parameters activated per target latent token. A generation-oriented data engine combines a knowledge-grounded visual vocabulary with large-scale visual clustering to balance semantic coverage and editing tasks, while training-time evaluation guides iterative data refinement. Bilingual annotations and verified editing supervision support progressive training up to native 1.5K resolution. We optimize generation and editing separately with rubric- and checklist-based rewards, then consolidate the specialized policies through noise-aware on-policy distillation. In the reported overall comparisons, the 1536-resolution model ranks first among the evaluated open-source models on PRISM-Bench, Qwen-Image-Bench, and UnicBench. MeanFlow-based few-step distillation yields WeLM-Image-Turbo, which generates a 1024×1024 image in 4.98,s on a single NVIDIA H20 GPU using eight guidance-free steps.
Figures & tables
Figure 1: Performance and efficiency overview of WeLM-Image . Left: Throughput (QPM/GPU) compared with representative baselines as the number of input images increases. Middle: Aggregate performance on a suite of image-generation benchmarks. Right: Aggregate performance on a suite of image-editing benchmarks.
Figure 2: Overview of the WeLM-Image architecture. Tokens on the understanding (UND) and generation (GEN) paths retain path-specific projections and experts while sharing masked self-attention over one packed multimodal sequence.
Figure 3: Representative source-ordered sequences under the unified interleaved task representation. Blue and green denote the UND path and GEN path, respectively. Orange underlining marks supervised segments. The dashed ViT segment is optional.
Model
Architecture
Reconstruction
Generation
COCO 512
ImageNet 512
In-house posters 1024
ImageNet 256
Params
Spatial
Ch.
PSNR ↑
SSIM ↑
PSNR ↑
SSIM ↑
PSNR ↑
SSIM ↑
FID ↓
IS ↑
Qwen-VAE [ 4 ]
126.89 M
8×
16
33.60
0.9249
32.96
0.9165
37.98
0.9658
15.29
84.62
FLUX-VAE [ 30 ]
83.82 M
8×
16
34.20
0.9486
33.91
0.9488
37.99
0.9771
27.63
55.10
FLUX.2-VAE [ 36 ]
84 M
8×
32
34.61
0.9540
34.34
0.9562
37.13
0.9780
9.87
90.85
NextStep-VAE [ 31 ]
83.82 M
8×
16
33.12
0.9263
32.65
0.9216
36.47
0.9644
22.94
62.80
Table 1: VAE reconstruction and generation. Best results are in bold and second-best are underlined. A dash indicates that generation was not evaluated.
Group
Configuration
UND path
GEN path
Backbone
Decoder layers
27
Hidden size
2,048
FFN layout
Layer 0 dense; Layers 1–26 MoE
Intermediate size
11,264 (dense); 1,408 (expert)
Experts per MoE layer
64 routed + 2 shared per path
Routing
Routed experts selected per token
6
20
Table 2: Configuration and parameter scale of the WeLM-Image MoT–MoE backbone. The UND path and GEN path use independent weights. The full-model total includes the ViT encoder and excludes the VAE.
Figure 4: Block-structured attention mask for a generation sequence containing prompt text, a condition image, CoT text, and a noisy target. Rows denote queries and columns denote keys/values; gray cells are visible and white cells are masked. Text blocks use causal attention, whereas the condition image and noisy target use bidirectional attention within their respective blocks. Each block can attend to preceding conditions, while noisy-target keys/values remain hidden from earlier blocks. Purple marks CoT tokens receiving cross-entropy supervision, and the inset shows isolation between packed samples.
Figure 5: Text-compatible unified 3D RoPE. (a) In token-coordinate space, text and ViT tokens remain on the diagonal (p,p,p) , whereas VAE tokens retain t=p and occupy a centered local h – w grid (p,p+Δh,p+Δw) . (b) The pretrained rotary channel pairs are assigned to t , h , and w in interleaved order, and the resulting three-axis RoPE is applied once to the rotary subspaces of queries and keys in each attention layer.
Figure 6: Overview of the data refinement, annotation, and training-mixture construction pipeline.
Figure 7: Scalable data infrastructure based on distributed COS storage, Ray services, Pulsar queues, ES retrieval, feature KV storage, and dynamic dataset assembly.
Figure 8: Resolution and internal aesthetic score distributions of the filtered 0.6B-image pool.
Figure 9: Representative samples from four AES score ranges. Images are center-cropped to a common aspect ratio for comparison. Each column contains four examples from the corresponding interval.
Figure 11: Illustration of task-aware edit tags used to guide editing-instruction construction.
Figure 12: Training pipeline of WeLM-Image. Pretraining uses T2T, I2T, T2I, and I2I. SFT retains T2I and I2I. Task-separated RL then specializes the two generation tasks before OPD and Meanflow distill the policies for deployment.
Stage
512
1024
1536
SFT
Optimization
Optimizer
AdamW [ 55 ] ( β1=0.9 , β2=0.95 , ϵ=10−15 )
Learning rate
10−4
10−4
10−4
2.5×10−5
LR scheduler
Constant
Constant
Constant
Constant
Warmup steps
2,500
500
500
500
Weight decay
0.01
0.01
0.01
0.01
Table 3: Training recipe of WeLM-Image. Generation pixels denotes the native-image area budget, and generation long edge gives the additional side cap. The product of FSDP shard and context-parallel size is held at 32 so that the parameter-shard width is unchanged when long-context training is enabled. Mixture percentages are normalized over understanding, text-to-image, editing, and multi-reference data.
Model Name
Steps
Text-to-Image
Image Editing (# input images)
1024×576
1024×768
1024×1024
1 img
2 imgs
3 imgs
4 imgs
Qwen-Image-2512-Lightning [ 4 ]
4
1.79
2.33
3.21
–
–
–
–
Qwen-Image-2512 [ 4 ]
50
35.82
47.81
67.13
–
–
–
–
Qwen-Image-Edit-2511-Lightning [ 4 ]
4
–
–
–
7.52
12.82
19.56
27.35
Qwen-Image-Edit-2511 [ 4 ]
40
–
–
–
133.04
233.24
360.18
510.64
Z-Image [ 49 ]
50
26.67
35.82
49.43
–
–
–
–
Table 4: End-to-end inference latency (seconds, lower is better) on NVIDIA H20 GPUs. Each entry is the mean wall-clock time over three timed runs following one warm-up run, and excludes model loading. Steps denotes the number of sampling steps. Editing cases are indexed by the number of input images, so one input image corresponds to instruction-guided single-image editing and two to four input images to multi-reference composition. All cases produce a 1024×1024 output. Lightning denotes the 4-step distillation LoRA of the respective base model. The Lightning configurations and WeLM-Image-Turbo are sampled guidance-free with true_cfg_scale =1 , so they perform one forward pass per step rather than the two required under classifier-free guidance. † Every configuration is served on a single GPU except HunyuanImage-3.0-Instruct-Distil, which requires a 4-way tensor-parallel instance spanning four GPUs . Its per-instance latency therefore corresponds to four times the accelerator cost of the other entries. It is run with bot_task = image and without external chain-of-thought prompt rewriting.
Model Name
GenEval ↑
OneIG ↑
PRISM ↑
LongText ↑
Qwen-Image-Bench ↑
WeGenBench ↑
GPT-Image-2
0.886
0.515
8.039
0.972
63.165
0.969
Nano-Banana-Pro
0.781
0.568
7.679
0.914
59.803
0.959
Qwen-Image-3.0
0.857
0.549
7.685
0.980
61.692
0.962
Seedream-5.0-Pro
0.864
0.532
7.421
0.947
59.591
0.968
Qwen-Image [ 4 ]
0.871
0.530
7.072
0.934
46.325
0.909
Qwen-Image-2512 [ 4 ]
0.747
0.521
6.888
0.954
49.444
0.897
Table 5: Quantitative evaluation results on Text-to-Image generation and Text Rendering benchmarks. Closed-source models including GPT-Image-2, Nano-Banana-Pro, Qwen-Image-3.0, and Seedream-5.0-Pro are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Single Obj.
Two Obj.
Counting
Colors
Position
Attr Bind.
Overall ↑
GPT-Image-2
0.9969
0.9621
0.8844
0.9043
0.8325
0.7375
0.8863
Nano-Banana-Pro
0.9844
0.8914
0.7219
0.7606
0.8250
0.5000
0.7806
Qwen-Image-3.0
0.9969
0.9444
0.8250
0.9309
0.7550
0.6900
0.8570
Seedream-5.0-Pro
0.9938
0.9444
0.7469
0.9149
0.8775
0.7050
0.8637
Qwen-Image
0.9906
0.9545
0.8875
0.8989
0.7675
0.7275
0.8711
Qwen-Image-2512
0.9844
0.9242
0.6188
0.8750
0.4750
0.6075
0.7475
Table 6: Detailed evaluation results on GenEval across different object-centric compositional skills. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Imagination
Entity
Style
Composition
Overall ↑
GPT-Image-2
7.48
8.20
8.08
8.54
8.04
Nano-Banana-Pro
7.06
7.78
7.74
8.11
7.68
Qwen-Image-3.0
6.95
7.80
7.64
8.18
7.68
Seedream-5.0-Pro
7.24
7.82
7.94
8.48
7.42
Qwen-Image
6.33
7.15
7.00
7.97
7.07
Qwen-Image-2512
6.47
7.04
7.02
8.10
6.89
Table 7: Detailed evaluation results on PRISM-Bench across reasoning and aesthetic dimensions. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Alignment
Text
Reasoning
Style
Diversity
Overall ↑
GPT-Image-2
0.8716
0.8402
0.3354
0.3633
0.1661
0.5153
Nano-Banana-Pro
0.8741
0.9406
0.3225
0.4589
0.2416
0.5675
Qwen-Image-3.0
0.8634
0.9419
0.3193
0.3998
0.2210
0.5491
Seedream-5.0-Pro
0.8735
0.8361
0.3216
0.4267
0.2036
0.5323
Qwen-Image
0.8569
0.9215
0.2826
0.4180
0.1719
0.5302
Qwen-Image-2512
0.8542
0.9864
0.2818
0.3433
0.1391
0.5210
Table 8: Detailed evaluation results on OneIG-Bench across fine-grained alignment dimensions. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Basic
Advanced
Designer
Overall
short ↑
long ↑
short ↑
long ↑
short ↑
long ↑
short ↑
long ↑
GPT-Image-2
0.8631
0.8568
0.8353
0.8347
0.9262
0.9139
0.8547
0.8509
Nano-Banana-Pro
0.8325
0.8473
0.7970
0.7994
0.8918
0.8769
0.8194
0.8240
Qwen-Image-3.0
0.8745
0.8417
0.8112
0.7847
0.8715
0.9157
0.8390
0.8183
Seedream-5.0-Pro
0.8410
0.8569
0.8057
0.8328
0.9067
0.9478
0.8287
0.8536
Qwen-Image
0.8217
0.8239
0.7995
0.8226
0.8694
0.8545
0.8146
0.8266
Table 9: Detailed evaluation results on TIIF-Bench. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Global
Entity
Attribute
Relation
Other
Overall ↑
GPT-Image-2
0.8344
0.9290
0.8966
0.9522
0.8554
0.8709
Nano-Banana-Pro
0.8359
0.9252
0.8939
0.9496
0.8640
0.8684
Qwen-Image-3.0
0.8511
0.9237
0.8944
0.9524
0.8629
0.8656
Seedream-5.0-Pro
0.8426
0.9308
0.8997
0.9497
0.9120
0.8732
Qwen-Image
0.8389
0.9383
0.9113
0.9516
0.8880
0.8881
Qwen-Image-2512
0.8480
0.9307
0.8928
0.9485
0.8880
0.8705
Table 10: Detailed evaluation results on DPG-Bench. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Quality
Aesthetics
Alignment
Creative Gen.
Overall ↑
GPT-Image-2
57.06
66.31
64.40
72.94
63.17
Nano-Banana-Pro
56.05
61.55
60.49
65.97
59.80
Qwen-Image-3.0
56.96
63.80
63.08
69.41
61.69
Seedream-5.0-Pro
55.57
61.93
61.10
64.98
59.59
Qwen-Image
47.39
48.61
47.28
41.01
46.33
Qwen-Image-2512
51.68
51.85
49.71
43.60
49.44
Table 11: Detailed evaluation results on Qwen-Image-Bench. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Alignments
Aesthetics
Visual Text Rendering
QA ↑
COT ↑
AM ↑
Simedit↑
Accsen↑
Scorequa↑
GNED ↑
CharF1↑
GPT-Image-2
0.97
8.95
2.84
0.50
0.57
0.88
0.52
0.56
Nano-Banana-Pro
0.97
8.71
2.77
0.38
0.55
0.86
0.45
0.49
Qwen-Image-3.0
0.96
8.76
2.76
0.51
0.46
0.92
0.55
0.58
Seedream-5.0-Pro
0.97
8.87
2.57
-
-
-
-
-
Qwen-Image
0.91
7.44
2.56
0.45
0.33
0.61
0.43
0.46
Table 12: Detailed evaluation results on WeGenBench. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
LongText-Bench
CVTG-2K
English
Chinese
Overall
NED
CLIPScore
Word Accuracy
GPT-Image-2
0.981
0.963
0.972
0.950
0.775
0.901
Nano-Banana-Pro
0.975
0.854
0.914
0.875
0.751
0.779
Qwen-Image-3.0
0.981
0.979
0.980
0.951
0.759
0.907
Seedream-5.0-Pro
0.943
0.951
0.947
0.860
0.761
0.762
Qwen-Image
0.936
0.932
0.934
0.915
0.813
0.834
Table 13: Detailed evaluation results on LongText-Bench and CVTG-2K. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
GEdit ↑
ImgEdit ↑
UnicBench ↑
WeGenEditBench ↑
GPT-Image-2
8.580
4.665
9.079
4.104
Nano-Banana-Pro
8.264
4.455
8.660
3.999
Qwen-Image-3.0
8.521
4.597
8.903
3.961
Seedream-5.0-Pro
8.460
4.650
8.906
4.160
HunyuanImage-3.0-Instruct-Distil [ 7 ]
8.101
4.552
8.481
3.791
HunyuanImage-3.0-Instruct-Distil-CoT [ 7 ]
8.385
4.523
8.577
3.872
Table 14: Quantitative comparison across single-image editing benchmarks. GEdit reports the average of the English and Chinese overall scores. ImgEdit and UnicBench report benchmark-level overall scores. WeGenEditBench reports the average of the text-editing and single-image editing subset scores. Closed-source models are excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
MICo
OmniContext
WeGenEditBench-Multi
W ↑
SC ↑
PQ ↑
Overall ↑
PF ↑
SC ↑
Overall ↑
EG ↑
PR ↑
VQ ↑
Overall ↑
GPT-Image-2
0.945
8.36
8.01
63.32
8.92
7.86
8.35
4.358
4.134
3.707
4.138
Nano-Banana-Pro
0.902
8.35
7.82
59.14
8.77
7.58
8.13
4.031
3.993
3.340
3.877
Qwen-Image-3.0
-
-
-
-
8.76
7.76
8.23
-
-
-
-
Seedream-5.0-Pro
0.938
8.19
7.86
60.56
8.74
7.62
8.13
4.270
4.093
3.750
4.095
HunyuanImage-3.0-Instruct-Distil
0.827
8.01
7.64
51.23
8.50
7.59
7.99
3.279
3.493
3.091
3.327
Table 15: Quantitative comparison across three multi-image editing benchmarks: MICo, OmniContext, and WeGenEditBench-Multi. Closed-source models are included for reference only and excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively. “–” denotes unavailable results due to input image limits.
Model Name
English
Chinese
SC ↑
PQ ↑
Overall ↑
SC ↑
PQ ↑
Overall ↑
GPT-Image-2
9.310
8.296
8.657
9.134
8.330
8.503
Nano-Banana-Pro
8.927
8.129
8.253
8.760
8.331
8.276
Qwen-Image-3.0
9.181
8.204
8.536
9.207
8.163
8.506
Seedream-5.0-Pro
9.068
8.274
8.426
9.109
8.299
8.494
HunyuanImage-3.0-Instruct-Distil
8.908
8.052
8.169
8.692
8.105
8.033
Table 16: Quantitative comparison on GEdit. Closed-source models are included for reference only and excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Action
Add
Adjust
BG
Compose
Extract
Remove
Replace
Style
Overall
GPT-Image-2
4.89
4.87
4.75
4.70
3.88
4.40
4.83
4.76
4.89
4.665
Nano-Banana-Pro
4.72
4.62
4.64
4.40
3.78
3.79
4.73
4.53
4.87
4.455
Qwen-Image-3.0
4.90
4.68
4.71
4.50
4.14
4.19
4.78
4.75
4.73
4.597
Seedream-5.0-Pro
4.78
4.79
4.78
4.73
4.43
3.79
4.89
4.76
4.90
4.650
HunyuanImage-3.0-Instruct-Distil
4.81
4.70
4.74
4.51
3.74
3.97
4.83
4.78
4.88
4.552
HunyuanImage-3.0-Instruct-Distil-CoT
4.63
4.76
4.84
4.53
3.42
4.01
4.87
4.77
4.87
4.523
Table 17: Quantitative comparison on ImgEdit. The nine subtask scores are reported with two decimal places, while Overall is reported with three decimal places. Closed-source models are included for reference only and excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
IF ↑
NC ↑
VQ ↑
RA ↑
Overall ↑
GPT-Image-2
9.626
8.979
8.877
9.000
9.079
Nano-Banana-Pro
9.233
8.693
8.473
8.210
8.660
Qwen-Image-3.0
9.252
9.264
8.643
8.040
8.903
Seedream-5.0-Pro
9.309
9.021
8.735
8.289
8.906
HunyuanImage-3.0-Instruct-Distil
8.783
9.085
8.261
7.264
8.481
HunyuanImage-3.0-Instruct-Distil-CoT
8.934
9.104
8.263
7.644
8.577
Table 18: Quantitative comparison on UnicBench. Closed-source models are included for reference only and excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
EG ↑
PR ↑
VQ ↑
DS ↑
Overall ↑
GPT-Image-2
4.298
4.049
4.463
4.182
4.076
Nano-Banana-Pro
4.159
3.752
4.370
4.050
3.882
Qwen-Image-3.0
4.120
3.469
4.331
4.126
3.813
Seedream-5.0-Pro
4.207
4.084
4.434
4.206
4.029
HunyuanImage-3.0-Instruct-Distil
4.020
4.175
4.280
3.952
3.841
HunyuanImage-3.0-Instruct-Distil-CoT
4.071
4.065
4.265
4.008
3.862
Table 19: Quantitative comparison on WeGenEditBench-single. EG, PR, VQ, and DS denote Edit Goal, Preservation, Visual Quality, and Domain-specific Capability, respectively. Closed-source models are included for reference only and excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Model Name
Text-side
Image-side
Overall
EG
PR
VQ
DS
EG
PR
VQ
DS
GPT-Image-2
4.289
4.031
4.329
4.399
4.604
3.919
4.421
4.452
4.132
Nano-Banana-Pro
4.295
4.092
4.310
4.322
4.396
4.208
4.232
4.306
4.116
Qwen-Image-3.0
4.367
3.732
4.329
4.385
4.509
3.869
4.406
4.414
4.109
Seedream-5.0-Pro
4.415
4.327
4.416
4.504
4.362
4.207
4.455
4.429
4.291
SenseNova-U1-8B-MoT-CoT
4.039
3.880
3.844
3.943
4.340
4.092
3.935
4.090
3.762
Table 20: Quantitative comparison on WeGenEditBench-text. Closed-source models are included for reference only and excluded from rank highlighting. Darker cell colors indicate better performance, with the three highlighted shades denoting the 1st, 2nd, and 3rd best results, respectively.
Figure 13: Qualitative results of WeLM-Image on text-to-image generation.
Figure 14: Qualitative results of WeLM-Image on image editing.
We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress, existing models still struggle with ultra-long text rendering, multilingual typography, high-resolution photorealism, robust instruction following, and efficient deployment, especially in text-rich and compositionally complex scenarios. Qwen-Image-2.0 addresses these challenges by coupling Qwen3-VL as the condition encoder with a Multimodal Diffusion Transformer for joint condition-target modeling, supported by large-scale data curation and a customized multi-stage training pipeline. This enables strong multimodal understanding while preserving flexible generation and editing capabilities. The model supports instructions of up to 1K tokens for generating text-rich content such as slides, posters, infographics, and comics, while significantly improving multilingual text fidelity and typography. It also enhances photorealistic generation with richer details, more realistic textures, and coherent lighting, and follows complex prompts more reliably across diverse styles. Extensive human evaluations show that Qwen-Image-2.0 substantially outperforms previous Qwen-Image models in both generation and editing, marking a step toward more general, reliable, and practical image generation foundation models.
We introduce Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family, comprising Base, Turbo, Edit, and Edit-Turbo variants. It delivers competitive performance in high-quality text-to-image generation, fast inference, instruction-based editing, and bilingual (Chinese-English) text rendering. Closed-source multimodal systems like Nano-Banana-Pro and GPT-Image-2 achieve strong performance through system-level integration rather than a single model, yet their internal practices remain largely undisclosed. In this work, we demonstrate that targeted improvements in model understanding, data quality, and training pipelines, coupled with agentic inference-time scaling, can substantially enhance generation and editing performance even under highly constrained compute budgets. Comprehensive evaluations show that Boogu-Image-0.1 consistently matches or surpasses other open-source models across standard benchmarks, and achieves results approaching leading closed-source systems. Notably, this is accomplished with only 208.62 million unique images. The base model's theoretical training cost is only approximately $400K. We share practical discussions that we believe are valuable to the broader research community, and release weights, code, and recipes under Apache 2.0 to advance the open ecosystem for unified multimodal understanding and generation. Our code is available here: https://github.com/Boogu-Project/Boogu-Image.
Most unified large multimodal models (LMMs) that support both visual understanding and image generation still rely on curated post-training supervision, such as human annotations, preference labels, or external reward models. We ask whether a unified LMM can improve both abilities autonomously using only unlabeled images. We propose a self-evolving training framework with three internal roles: a Proposer that generates visual questions, a Solver that answers and evaluates them, and a Generator that synthesizes images. Training uses only self-derived consistency signals, without human annotations, preference labels, or task-trained external reward/judge models. To stabilize learning, we introduce Solver Token Entropy (STE), a continuous difficulty signal based on token-level prediction uncertainty that remains useful even when sample-level consistency becomes unreliable. For image generation, we design a multi-scale internal evaluation scheme that combines question-answer fidelity scoring with cycle-consistent captioning. This creates a solver-mediated coupling, where better visual understanding enables more reliable generation assessment and stronger internal training signals. The framework preserves the same role decomposition, reward logic, and training schedule across diffusion-based BLIP3o, rectified-flow BAGEL, and autoregressive VARGPT-v1.1 architectures, requiring only each backbone's native prompting and generation interface. Across eight understanding metrics, our method consistently improves over the corresponding base models. On BAGEL, it achieves a +3.5% absolute gain on MMMU and improves GenEval image generation performance from 82% to 85%. Code and models are publicly released.