from diffusers import ControlNetModel, StableDiffusionControlNetPipeline
controlnet = ControlNetModel.from_pretrained("777Radik/Qwen-Image-Cyrillic-ControlNet")
pipe = StableDiffusionControlNetPipeline.from_pretrained(
"Qwen/Qwen-Image-2512", controlnet=controlnet
)Qwen-Image Cyrillic Blockwise ControlNet
Blockwise Canny ControlNet checkpoint fine-tuned for copying real Cyrillic glyph controls
into Qwen-Image output. It starts from
DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny and keeps the DiffSynth checkpoint
key layout.
Artifact
model.safetensors- 2,266,838,080 bytes
- SHA-256:
8f7ed8860b94283d48b72859cb7ec715a6da7ae522a4a312004e635abfc8f9cb
Training
- base:
Qwen/Qwen-Image-2512 - trainable module: full
blockwise_controlnet - 128 prepared edge-control samples at 512×512
- 128 steps
- learning rate:
1e-5 - trainable precision: BF16
- frozen transformer, text encoder, and VAE storage/onload: FP8
- gradient checkpointing enabled
Exact hashes and arguments are in the separate configuration repository.
Validation
Fixed held-out benchmark: 100 unseen Russian words, 512×512, 20 steps, seed 3000 plus sample index, fitted edge control, scale 0.85.
- manual exact Cyrillic score: 99/100
- OCR diagnostic exact: 77/100
- mean OCR CER: 0.1142
- mean glyph similarity: 0.9564
The single manual failure was ЕЩЁ → ЁЩЁ. Edge scale retries 0.9, 1.0, and 1.1 and a
filled-control retry at 0.7 with the same seed did not correct it. OCR is diagnostic only;
the reported 99/100 score comes from manual inspection of all five contact sheets.
Limitations
Training data uses a narrow synthetic typography distribution: simple backgrounds, limited fonts, and isolated words. This checkpoint is intended for glyph-guided generation, not unguided spelling, paragraphs, arbitrary layouts, handwriting, or guaranteed OCR-perfect output.
- Downloads last month
- 7
Model tree for 777Radik/Qwen-Image-Cyrillic-ControlNet
Base model
Qwen/Qwen-Image-2512