Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Still work in progress, checkpoints are being uploaded on the go
Model source
Source description
2025-11-08 03-09-06 (0-00-14-28)
Still work in progress, checkpoints are being uploaded on the go
Current best: LoRA A: qwen-edit-enhance_64-v3_000001000, LoRA B: qwen-edit-enhance_000004250
LoRA A: /1000, LoRA B: /4750
Sources
1 sourceVerified Oct 14
Model artifacts
24 artifactsSource excerpts
2 excerptsLoRA A and LoRA B are meant to be wired one after another
Comfy workflow is in the files
Demo: 🤗 Click here
Prompt: Enhance image quality, followed by textual description of the scene. The more descriptive it is, the better the upscale effect will be
All images below are from 8 step Lighting LoRA.
Trained on a filtered subset of Unsplash-Lite and UltraHR-100K at 2.4MP
- Low resolution up to 16x
- Oversharpened images
- Noise up to 50%
- Gaussian blur radius up to 3px
- JPEG artifacts with quality as low as 5%
- Motion blur up to 64px
- Pixelation up to 16x
- Color bands up to 3 bits
- Images after upscale models - up to 16x
Not trained on: 2d, illustrations, artworks, text, graphics, CGI
2025-11-08 03-09-07 (0-00-02-28)
2025-11-08 03-09-06 (0-00-29-02)
2025-11-08 03-09-06 (0-00-35-15)
2025-11-08 03-09-06 (0-00-56-16)
2025-11-08 03-09-06 (0-01-09-04)
archive/qwen-edit-enhance_000004000.safetensors
safetensors · 2.20 GB · SHA-256 a9658cb13040…43a5 · Hugging Face
Downloadarchive/qwen-edit-enhance_000007000.safetensors
safetensors · 4.39 GB · SHA-256 cf2201e38be7…94b3 · Hugging Face
Downloadarchive/qwen-edit-enhance_64-v3_000001500.safetensors
safetensors · 1.10 GB · SHA-256 975b860dfac2…b1dd · Hugging Face
Downloadarchive/qwen-edit-enhance-v4_a_000001000.safetensors
safetensors · 2.20 GB · SHA-256 2c79b211416d…8185 · Hugging Face
Downloadarchive/qwen-edit-enhance-v4_b_000001000.safetensors
safetensors · 2.20 GB · SHA-256 680153cecfcd…7534 · Hugging Face
Downloadarchive/qwen-edit-enhance-v4_b_000002000.safetensors
safetensors · 2.20 GB · SHA-256 5de2f03590e6…e955 · Hugging Face
Downloadarchive/qwen-edit-enhance-v4_b_000004500.safetensors
safetensors · 2.20 GB · SHA-256 a50f59b96114…2fd1 · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-16_a_000001500.safetensors
safetensors · 281 MB · SHA-256 75052502f2d9…909e · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-16_a_000002000.safetensors
safetensors · 281 MB · SHA-256 9d1f5944b7df…ddef · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-16_a_000002500.safetensors
safetensors · 281 MB · SHA-256 3b943384334e…033a · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-16_a_000003000.safetensors
safetensors · 281 MB · SHA-256 648059958cee…2dca · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-16_b_000001250.safetensors
safetensors · 281 MB · SHA-256 36e68bae549b…ec8e · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-64_a_000000500.safetensors
safetensors · 1.10 GB · SHA-256 aa61444d125c…cd65 · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-64_a_000001000.safetensors
safetensors · 1.10 GB · SHA-256 c30315179b06…b195 · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-64_a_000002000.safetensors
safetensors · 1.10 GB · SHA-256 decf5cee6c15…b0e9 · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-64_a_000003000.safetensors
safetensors · 1.10 GB · SHA-256 228013f2739d…d034 · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-64_a_000003750.safetensors
safetensors · 1.10 GB · SHA-256 4ba25bbe25f2…004d · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-64_a_000004000.safetensors
safetensors · 1.10 GB · SHA-256 b7dbaea97e5e…31ca · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-64_a_000004750.safetensors
safetensors · 1.10 GB · SHA-256 82d67fbae615…300a · Hugging Face
Downloadarchive/qwen-edit-enhance-v4-64_b_000002750.safetensors
safetensors · 1.10 GB · SHA-256 33622ceb6ae8…daa4 · Hugging Face
Downloadqwen-edit-enhance_000004250.safetensors
safetensors · 2.20 GB · SHA-256 a6477a4621c8…77ef · Hugging Face
Downloadqwen-edit-enhance_64-v3_000001000.safetensors
safetensors · 1.10 GB · SHA-256 75d02e00eece…4f40 · Hugging Face
Download--- datasets: - zhihefang/UltraHR-100K - 1aurent/unsplash-lite base_model: - Qwen/Qwen-Image-Edit-2509 license: gpl-3.0 library_name: diffusers tags: - lora pipeline_tag: image-to-image ---  **Still work in progress, checkpoints are being uploaded on the go** **Current best:** LoRA A: qwen-edit-enhance_64-v3_000001000, LoRA B: qwen-edit-enhance_000004250 **V4 Candidates** LoRA A: [qwen-edit-enhance-v4-16_a_000003000](https://huggingface.co/vafipas663/Qwen-Edit-2509-Upscale-LoRA/blob/main/archive/qwen-edit-enhance-v4-16_a_000003000.safetensors)/1000, LoRA B: [qwen-edit-enhance-v4-64_a_000003750](https://huggingface.co/vafipas663/Qwen-Edit-2509-Upscale-LoRA/blob/main/archive/qwen-edit-enhance-v4-64_a_000003750.safetensors)/4750 LoRA A and LoRA B are meant to be wired one after another Comfy workflow [is in the files](https://huggingface.co/vafipas663/Qwen-Edit-2509-Upscale-LoRA/blob/main/Qwen-Edit-Upscale.json) Demo: 🤗 [Click here](https://huggingface.co/spaces/akhaliq/Qwen-Edit-2509-Upscale-LoRA) Prompt: Enhance image quality, followed by textual description of the scene. The more descriptive it is, the better the upscale effect will be All images below are from 8 step Lighting LoRA. * ModelSamplingAuraFlow is a must, shift must be kept **below** 0.3. With higher resolutions, such as image 3, you can set it as low as 0.02 * Samplers - LCM (best), Euler_Ancestral, then Euler * Schedulers all work and give varying results in terms of smoothness Trained on a filtered subset of Unsplash-Lite and UltraHR-100K at 2.4MP * Style: photography * Subjects include: landscapes, architecture, interiors, portraits, plants, vehicles, abstract photos, man-made objects, food * Trained to recover from: > * Low resolution up to 16x > * Oversharpened images > * Noise up to 50% > * Gaussian blur radius up to 3px > * JPEG artifacts with quality as low as 5% > * Motion blur up to 64px > * Pixelation up to 16x > * Color bands up to 3 bits > * Images after upscale models - up to 16x Not trained on: 2d, illustrations, artworks, text, graphics, CGI  