konieshadow/fooocus-api-realistic 📝🖼️🔢❓ → 🖼️
About
Third party Fooocus replicate model with preset 'realistic'
Example Output
Prompt:
"1 girl"
Output
Performance Metrics
9.90s
Prediction Time
9.94s
Total Time
All Input Parameters
{
"prompt": "1 girl",
"cn_type1": "ImagePrompt",
"cn_type2": "ImagePrompt",
"cn_type3": "ImagePrompt",
"cn_type4": "ImagePrompt",
"sharpness": 2,
"image_seed": 6091967260935476000,
"uov_method": "Disabled",
"image_number": 1,
"guidance_scale": 3,
"refiner_switch": 0.5,
"negative_prompt": "unrealistic, saturated, high contrast, big nose, painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label",
"style_selections": "Fooocus V2,Fooocus Photograph,Fooocus Negative",
"uov_upscale_value": 0,
"outpaint_selections": "",
"outpaint_distance_top": 0,
"performance_selection": "Speed",
"outpaint_distance_left": 0,
"aspect_ratios_selection": "1152*896",
"outpaint_distance_right": 0,
"outpaint_distance_bottom": 0,
"inpaint_additional_prompt": ""
}
Input Parameters
- prompt
- Prompt for image generation
- cn_img1
- Input image for image prompt. If all cn_img[n] are None, image prompt will not applied.
- cn_img2
- Input image for image prompt. If all cn_img[n] are None, image prompt will not applied.
- cn_img3
- Input image for image prompt. If all cn_img[n] are None, image prompt will not applied.
- cn_img4
- Input image for image prompt. If all cn_img[n] are None, image prompt will not applied.
- cn_stop1
- Stop at for image prompt, None for default value
- cn_stop2
- Stop at for image prompt, None for default value
- cn_stop3
- Stop at for image prompt, None for default value
- cn_stop4
- Stop at for image prompt, None for default value
- cn_type1
- ControlNet type for image prompt
- cn_type2
- ControlNet type for image prompt
- cn_type3
- ControlNet type for image prompt
- cn_type4
- ControlNet type for image prompt
- sharpness
- cn_weight1
- Weight for image prompt, None for default value
- cn_weight2
- Weight for image prompt, None for default value
- cn_weight3
- Weight for image prompt, None for default value
- cn_weight4
- Weight for image prompt, None for default value
- image_seed
- Seed to generate image, -1 for random
- uov_method
- image_number
- How many image to generate
- guidance_scale
- refiner_switch
- negative_prompt
- Negtive prompt for image generation
- uov_input_image
- Input image for upscale or variation, keep None for not upscale or variation
- style_selections
- Fooocus styles applied for image generation, seperated by comma
- uov_upscale_value
- Only when Upscale (Custom)
- inpaint_input_mask
- Input mask for inpaint
- inpaint_input_image
- Input image for inpaint or outpaint, keep None for not inpaint or outpaint. Please noticed, `uov_input_image` has bigger priority is not None.
- outpaint_selections
- Outpaint expansion selections, literal 'Left', 'Right', 'Top', 'Bottom' seperated by comma
- outpaint_distance_top
- Outpaint expansion distance from Top of the image
- performance_selection
- Performance selection
- outpaint_distance_left
- Outpaint expansion distance from Left of the image
- aspect_ratios_selection
- The generated image's size
- outpaint_distance_right
- Outpaint expansion distance from Right of the image
- outpaint_distance_bottom
- Outpaint expansion distance from Bottom of the image
- inpaint_additional_prompt
- Prompt for image generation
Output Schema
Output
Example Execution Logs
[Predictor Predict] Params: {'prompt': '1 girl', 'negative_prompt': 'unrealistic, saturated, high contrast, big nose, painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label', 'style_selections': ['Fooocus V2', 'Fooocus Photograph', 'Fooocus Negative'], 'performance_selection': 'Speed', 'aspect_ratios_selection': '1152*896', 'image_number': 1, 'image_seed': 6091967260935476000, 'sharpness': 2.0, 'guidance_scale': 3.0, 'base_model_name': 'realisticStockPhoto_v10.safetensors', 'refiner_model_name': 'None', 'refiner_switch': 0.5, 'loras': [['SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors', 0.25]], 'uov_input_image': None, 'uov_method': 'Disabled', 'upscale_value': 0.0, 'outpaint_selections': [], 'outpaint_distance_left': 0, 'outpaint_distance_right': 0, 'outpaint_distance_top': 0, 'outpaint_distance_bottom': 0, 'inpaint_input_image': None, 'inpaint_additional_prompt': '', 'image_prompts': [], 'advanced_params': [False, 1.5, 0.8, 0.3, 7.0, 'dpmpp_2m_sde_gpu', 'karras', False, -1, -1, -1, -1, -1, -1, False, False, False, False, 0.25, 64, 128, 'joint', False, None, None, None, None, False, False, 'v2.6', 1.0, 0.618]}
[Task Queue] Task queue is free, start task, seq=3
[Parameters] Adaptive CFG = 7.0
[Parameters] Sharpness = 2.0
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] CFG = 3.0
[Parameters] Seed = 6091967260935476000
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 30 - 15
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] 1 girl, full focus, beautiful, elegant, breathtaking, highly detailed, cinematic, light, clear, perfect, coherent, color, epic, cute, gorgeous, symmetry, beaten, winning, romantic, artistic, fine detail, intricate, enhanced, complex, colorful, cool, awesome, inspired, professional, creative, brilliant, expressive, vibrant, passionate, iconic, brave
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Parameters] Denoising Strength = 1.0
[Parameters] Initial Latent shape: Image Space (896, 1152)
Preparation time: 0.75 seconds
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 14.614643096923828
0%| | 0/30 [00:00<?, ?it/s]
3%|▎ | 1/30 [00:00<00:06, 4.34it/s]
7%|▋ | 2/30 [00:00<00:06, 4.35it/s]
10%|█ | 3/30 [00:00<00:06, 4.34it/s]
13%|█▎ | 4/30 [00:00<00:05, 4.34it/s]
17%|█▋ | 5/30 [00:01<00:05, 4.33it/s]
20%|██ | 6/30 [00:01<00:05, 4.33it/s]
23%|██▎ | 7/30 [00:01<00:05, 4.33it/s]
27%|██▋ | 8/30 [00:01<00:05, 4.32it/s]
30%|███ | 9/30 [00:02<00:04, 4.31it/s]
33%|███▎ | 10/30 [00:02<00:04, 4.31it/s]
37%|███▋ | 11/30 [00:02<00:04, 4.31it/s]
40%|████ | 12/30 [00:02<00:04, 4.31it/s]
43%|████▎ | 13/30 [00:03<00:03, 4.30it/s]
47%|████▋ | 14/30 [00:03<00:03, 4.30it/s]
50%|█████ | 15/30 [00:03<00:03, 4.30it/s]
53%|█████▎ | 16/30 [00:03<00:03, 4.30it/s]
57%|█████▋ | 17/30 [00:03<00:03, 4.30it/s]
60%|██████ | 18/30 [00:04<00:02, 4.30it/s]
63%|██████▎ | 19/30 [00:04<00:02, 4.29it/s]
67%|██████▋ | 20/30 [00:04<00:02, 4.29it/s]
70%|███████ | 21/30 [00:04<00:02, 4.29it/s]
73%|███████▎ | 22/30 [00:05<00:01, 4.28it/s]
77%|███████▋ | 23/30 [00:05<00:01, 4.28it/s]
80%|████████ | 24/30 [00:05<00:01, 4.28it/s]
83%|████████▎ | 25/30 [00:05<00:01, 4.27it/s]
87%|████████▋ | 26/30 [00:06<00:00, 4.28it/s]
90%|█████████ | 27/30 [00:06<00:00, 4.28it/s]
93%|█████████▎| 28/30 [00:06<00:00, 4.27it/s]
97%|█████████▋| 29/30 [00:06<00:00, 4.29it/s]
100%|██████████| 30/30 [00:06<00:00, 4.30it/s]
100%|██████████| 30/30 [00:06<00:00, 4.30it/s]
Image generated with private log at: /src/repositories/Fooocus/outputs/2023-12-26/log.html
Generating and saving time: 7.61 seconds
[Task Queue] Finish task, seq=3
[Predictor Predict] Finished with 1 images
Version Details
- Version ID
612fd74b69e6c030e88f6548848593a1aaabe16a09cb79e6d714718c15f37f47- Version Created
- January 19, 2024