Loading…
Loading…
Qwen/Qwen-Image-Edit-2509A pre-merged, quantized build of Qwen-Image-Edit-2509 with two fine-tunes baked into the weights:
A standard edit showing the base capability is intact:
| Prompt: A giant full-body teddy bear wearing a plain white t-shirt. Print the exact logo from the input image onto the front of the t-shirt, large and clearly visible. Soft studio lighting, clean light-gray background, full-body shot, cute and detailed. | |
| Prompt: Show this exact teddy bear in one image as three separate full-body views in a row, evenly spaced: front view facing the camera, left side view, and back view facing away from the camera. In every view the head faces the same direction as the body — in the back view the head is also turned away from the camera and the face is completely hidden. Keep the character design, white t-shirt with the Qwen logo, lighting style, and light gray background perfectly consistent across all three views. | |
| Original | Prompt: This exact teddy bear seen from directly behind — keep the same back view as the input image, do not rotate or turn the bear. Single full-body view, higher detail. Keep the character design, white t-shirt, lighting style, and light gray background exactly consistent. |
| Prompt: Show this exact teddy bear seen from its left side, a single full-body view. Keep the character design, white t-shirt, lighting style, and light gray background exactly consistent with the input image. | Prompt: Show this exact teddy bear seen from its right side, a single full-body view. Keep the character design, white t-shirt, lighting style, and light gray background exactly consistent with the input image. |
| Component | File | ~Size | Download |
|---|---|---|---|
| Transformer | qwen-image-edit-2509-turbo-multiple-angles-Q6_K.gguf |
11.4 GB | Link |
| Text Encoder | Qwen2.5-VL-7B-Instruct-q4_0.gguf |
4.43 GB | Link |
| mmproj | Qwen2.5-VL-7B-Instruct-mmproj-f16.gguf |
1.35 GB | Link |
| VAE | qwen_image_vae.safetensors |
254 MB | Link |
| Parameter | Value |
|---|---|
| Resolution | 1024 × 1024 |
| Steps | 12 |
| CFG | 1.0 |
| Seed | 42 |
In comfy:
llama-quantize), gguf Python package