Open ZIYOU2222 opened 1 year ago
That looks like the live preview image. The final image is probably stored in the output folders.
At 5 steps, that might be the final image. What happens when you increase the steps to 10 or 20?
you need more steps more than likely
Hello, any update on this? I tried with img2img it's the same. Here's my config (without "init image"):
"seed": -1, "subseed": -1, "subseed_strength": 0, "seed_resize_from_h": -1, "seed_resize_from_w": -1, "sampler_name": "", "batch_size": 1, "n_iter": 1, "steps": 30, "cfg_scale": 7, "width": 512, "height": 512, "restore_faces": false, "tiling": false, "do_not_save_samples": false, "do_not_save_grid": false, "eta": 0, "s_min_uncond": 0, "s_churn": 0, "s_tmax": 0, "s_tmin": 0, "s_noise": 1, "override_settings": {}, "override_settings_restore_afterwards": true, "script_args": [], "sampler_index": "Euler a", "include_init_images": false, "script_name": "", "send_images": true, "save_images": true, "alwayson_scripts": {}
Is there an existing issue for this?
What happened?
When I call the api, what I return is a blurred picture, not the result of the final picture
url = "http://127.0.0.1:7860"
payload = { "prompt": "puppy dog", "steps": 5 }
response = requests.post(url=f'{url}/sdapi/v1/txt2img', json=payload)
r = response.json()
for i in r['images']: image = Image.open(io.BytesIO(base64.b64decode(i.split(",",1)[0])))
Steps to reproduce the problem
Call the API to generate the image
What should have happened?
Returns the final image
Commit where the problem happens
no
What platforms do you use to access the UI ?
Windows
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
List of extensions
no
Console logs
Additional information
No response