vetkastar/fooocus 📝🖼️🔢❓✓ → ❓

▶️ 395.7K runs 📅 Apr 2024 ⚙️ Cog 0.13.6 🔗 GitHub ⚖️ License

image-inpainting image-to-image text-to-image

About

Image generation, Added: inpaint_strength loras_custom_urls

Example Output

Prompt:

"woman, illustration, cartoon, soothing tones, calm colors, flowers"

Output

{"paths":["https://replicate.delivery/pbxt/9lfWVEcL5U2rTSBeEkl0b6Em1BaPIfHsz4wdSrfcEV93ksmKB/54ac8e55-bd01-480b-8727-553c89222020.png"],"seeds":["7569250874445648405"]}

Performance Metrics

10.96s Prediction Time

11.00s Total Time

All Input Parameters

{
  "prompt": "woman, illustration, cartoon, soothing tones, calm colors, flowers",
  "cn_type1": "ImagePrompt",
  "cn_type2": "ImagePrompt",
  "cn_type3": "ImagePrompt",
  "cn_type4": "ImagePrompt",
  "sharpness": 2,
  "image_seed": -1,
  "uov_method": "Disabled",
  "image_number": 1,
  "guidance_scale": 7,
  "refiner_switch": 0.5,
  "negative_prompt": "",
  "inpaint_strength": 0.5,
  "style_selections": "Fooocus V2,Fooocus Enhance,Fooocus Sharp",
  "loras_custom_urls": "",
  "uov_upscale_value": 0,
  "use_default_loras": true,
  "outpaint_selections": "",
  "outpaint_distance_top": 0,
  "performance_selection": "Speed",
  "outpaint_distance_left": 0,
  "aspect_ratios_selection": "1024*1024",
  "outpaint_distance_right": 0,
  "outpaint_distance_bottom": 0,
  "inpaint_additional_prompt": ""
}

Input Parameters

prompt Type: stringDefault:: Prompt for image generation
cn_img1 Type: string: Input image for image prompt. If all cn_img[n] are None, image prompt will not applied.
cn_img2 Type: string: Input image for image prompt. If all cn_img[n] are None, image prompt will not applied.
cn_img3 Type: string: Input image for image prompt. If all cn_img[n] are None, image prompt will not applied.
cn_img4 Type: string: Input image for image prompt. If all cn_img[n] are None, image prompt will not applied.
cn_stop1 Type: numberRange: 0 - 1: Stop at for image prompt, None for default value
cn_stop2 Type: numberRange: 0 - 1: Stop at for image prompt, None for default value
cn_stop3 Type: numberRange: 0 - 1: Stop at for image prompt, None for default value
cn_stop4 Type: numberRange: 0 - 1: Stop at for image prompt, None for default value
cn_type1 Default: ImagePrompt: ControlNet type for image prompt
cn_type2 Default: ImagePrompt: ControlNet type for image prompt
cn_type3 Default: ImagePrompt: ControlNet type for image prompt
cn_type4 Default: ImagePrompt: ControlNet type for image prompt
sharpness Type: numberDefault: 2Range: 0 - 30
cn_weight1 Type: numberRange: 0 - 2: Weight for image prompt, None for default value
cn_weight2 Type: numberRange: 0 - 2: Weight for image prompt, None for default value
cn_weight3 Type: numberRange: 0 - 2: Weight for image prompt, None for default value
cn_weight4 Type: numberRange: 0 - 2: Weight for image prompt, None for default value
image_seed Type: integerDefault: -1: Seed to generate image, -1 for random
uov_method Default: Disabled
adaptive_cfg Type: numberDefault: 7Range: 1 - 30: Adaptive CFG (Classifier-Free Guidance). Allows dynamically adjusting the strength of guidance during the generation process.
image_number Type: integerDefault: 1Range: 1 - 8: How many image to generate
sampler_name Type: stringDefault: dpmpp_2m_sde_gpu: Sampler. Choose a specific sampler for the diffusion process, affecting the quality and style of generated images.
adm_scaler_end Type: numberDefault: 0.3Range: 0 - 1: ADM Guidance End At Step. Determines at which stage of the generation process the ADM scaling stops being applied.
guidance_scale Type: numberDefault: 4Range: 1 - 30
inpaint_engine Type: stringDefault: v2.6: Inpaint Engine. Select a specific engine for inpainting, affecting the quality and style of results.
overwrite_step Type: integerDefault: -1Range: -1 - 200: Forced Overwrite of Sampling Step. Override the default number of sampling steps, affecting detail and generation time.
refiner_switch Type: numberDefault: 0.5Range: 0.1 - 1
scheduler_name Type: stringDefault: karras: Scheduler. Choose a specific scheduler for the diffusion process, affecting the quality and style of generated images.
negative_prompt Type: stringDefault:: Negative prompt for image generation
overwrite_width Type: integerDefault: -1Range: -1 - 2048: Forced Overwrite of Generating Width. Precisely set the desired width of the generated image.
uov_input_image Type: string: Input image for upscale or variation, keep None for not upscale or variation
inpaint_strength Type: numberDefault: 0.5Range: 0 - 1: Inpaint Denoising Strength
overwrite_height Type: integerDefault: -1Range: -1 - 2048: Forced Overwrite of Generating Height. Precisely set the desired height of the generated image.
overwrite_switch Type: numberDefault: -1Range: -1 - 1: Forced Overwrite of Refiner Switch Step. Override the moment of switching between the base model and the refiner model.
style_selections Type: stringDefault: Fooocus V2,Fooocus Enhance,Fooocus Sharp: Fooocus styles applied for image generation, separated by comma
loras_custom_urls Type: stringDefault:: Custom LoRAs URLs in the format 'url,weight' provide multiple seperated by ; (example 'url1,0.3;url2,0.1')
uov_upscale_value Type: numberDefault: 0: Only when Upscale (Custom)
use_default_loras Type: booleanDefault: true: Use default LoRAs
inpaint_input_mask Type: string: Input mask for inpaint
adm_scaler_negative Type: numberDefault: 0.8Range: 0.1 - 3: Negative ADM Guidance Scaler. Adjusts the influence of negative prompts in the ADM generation process.
adm_scaler_positive Type: numberDefault: 1.5Range: 0.1 - 3: Positive ADM Guidance Scaler. Adjusts the influence of positive prompts in the ADM (Attention-Driven Mechanism) generation process.
canny_low_threshold Type: integerDefault: 64Range: 1 - 255: Canny Low Threshold. For fine-tuning the Canny Edge Detection algorithm used in some ControlNet modes.
controlnet_softness Type: numberDefault: 0.25Range: 0 - 1: Softness of ControlNet. Adjust the 'softness' of ControlNet's influence on the final image.
inpaint_input_image Type: string: 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 Type: stringDefault:: Outpaint expansion selections, literal 'Left', 'Right', 'Top', 'Bottom' separated by comma
canny_high_threshold Type: integerDefault: 128Range: 1 - 255: Canny High Threshold. For fine-tuning the Canny Edge Detection algorithm used in some ControlNet modes.
invert_mask_checkbox Type: booleanDefault: false: Invert Mask. Invert the mask during inpainting, providing additional control over the process.
outpaint_distance_top Type: integerDefault: 0: Outpaint expansion distance from Top of the image
performance_selection Default: Speed: Performance selection
outpaint_distance_left Type: integerDefault: 0: Outpaint expansion distance from Left of the image
aspect_ratios_selection Default: 1152*896: The generated image's size
inpaint_erode_or_dilate Type: integerDefault: 0Range: -64 - 64: Mask Erode or Dilate. Erode or dilate the inpainting mask for fine-tuning the area of inpainting application.
outpaint_distance_right Type: integerDefault: 0: Outpaint expansion distance from Right of the image
overwrite_vary_strength Type: numberDefault: -1Range: -1 - 1: Forced Overwrite of Denoising Strength of "Vary". Precisely control the strength of variation when using the "Vary" function.
inpaint_respective_field Type: numberDefault: 1Range: 0 - 1: Inpaint Respective Field. Control the size of the influence area during inpainting.
outpaint_distance_bottom Type: integerDefault: 0: Outpaint expansion distance from Bottom of the image
skipping_cn_preprocessor Type: booleanDefault: false: Skip Preprocessors. Ability to skip ControlNet preprocessing, useful for development and testing.
debugging_cn_preprocessor Type: booleanDefault: false: Debug Preprocessors. For debugging ControlNet preprocessing.
inpaint_additional_prompt Type: stringDefault:: Prompt for image generation
overwrite_upscale_strength Type: numberDefault: -1Range: -1 - 1: Forced Overwrite of Denoising Strength of "Upscale". Precise control of denoising strength when upscaling images.
debugging_inpaint_preprocessor Type: booleanDefault: false: Debug Inpaint Preprocessing. For debugging and controlling preprocessing during inpainting.
inpaint_disable_initial_latent Type: booleanDefault: false: Disable initial latent in inpaint. For controlling preprocessing during inpainting.
mixing_image_prompt_and_inpaint Type: booleanDefault: false: Mixing Image Prompt and Inpaint. Allow mixing the image prompt with inpaint functions for more complex effects.
mixing_image_prompt_and_vary_upscale Type: booleanDefault: false: Mixing Image Prompt and Vary/Upscale. Allow mixing the image prompt with vary/upscale functions for more complex effects.

Output Schema

paths Type: arrayItems: string: Paths
seeds Type: arrayItems: string: Seeds

Example Execution Logs

[Predictor Predict] Params: {'prompt': 'woman, illustration, cartoon, soothing tones, calm colors, flowers', 'negative_prompt': '', 'style_selections': ['Fooocus V2', 'Fooocus Enhance', 'Fooocus Sharp'], 'performance_selection': 'Speed', 'aspect_ratios_selection': '1024*1024', 'image_number': 1, 'image_seed': -1, 'sharpness': 2.0, 'guidance_scale': 7.0, 'base_model_name': 'juggernautXL_v8Rundiffusion.safetensors', 'refiner_model_name': 'None', 'refiner_switch': 0.5, 'loras': [['sd_xl_offset_example-lora_1.0.safetensors', 0.1]], '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': [], 'save_extension': 'png', 'require_base64': False, 'advanced_params': AdvancedParams(disable_preview=False, disable_intermediate_results=False, disable_seed_increment=False, adm_scaler_positive=1.5, adm_scaler_negative=0.8, adm_scaler_end=0.3, adaptive_cfg=7.0, sampler_name='dpmpp_2m_sde_gpu', scheduler_name='karras', overwrite_step=-1, overwrite_switch=-1, overwrite_width=-1, overwrite_height=-1, overwrite_vary_strength=-1, overwrite_upscale_strength=-1, mixing_image_prompt_and_vary_upscale=False, mixing_image_prompt_and_inpaint=False, debugging_cn_preprocessor=False, skipping_cn_preprocessor=False, canny_low_threshold=64, canny_high_threshold=128, refiner_swap_method='joint', controlnet_softness=0.25, freeu_enabled=False, freeu_b1=1.01, freeu_b2=1.02, freeu_s1=0.99, freeu_s2=0.95, debugging_inpaint_preprocessor=False, inpaint_disable_initial_latent=False, inpaint_engine='v2.6', inpaint_strength=0.5, inpaint_respective_field=1.0, inpaint_mask_upload_checkbox=False, invert_mask_checkbox=False, inpaint_erode_or_dilate=0)}
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Task Queue] Waiting for task finished, job_id=3d589dae-0a96-4347-b017-b064ff961474[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Task Queue] Task queue start task, job_id=3d589dae-0a96-4347-b017-b064ff961474[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] Adaptive CFG = 7.0[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] Sharpness = 2.0[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] ControlNet Softness = 0.25[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] ADM Scale = 1.5 : 0.8 : 0.3[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] CFG = 7.0[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] Seed = 7569250874445648405[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] Sampler = dpmpp_2m_sde_gpu - karras[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] Steps = 30 - 15[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Fooocus] Initializing ...[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Fooocus] Loading models ...[0m
Refiner unloaded.
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Fooocus] Processing prompts ...[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Fooocus] Preparing Fooocus text #1 ...[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Prompt Expansion] woman, illustration, cartoon, soothing tones, calm colors, flowers, detailed, dramatic, background, complimentary atmosphere, romantic, full color, beautiful, sharp focus, very inspirational, thought, perfect composition, dynamic light, epic, cinematic, winning, illuminated, amazing, creative, elegant, intricate, loving, symmetry, brave, awesome, scenic, highly determined, passionate[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Fooocus] Encoding positive #1 ...[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Fooocus] Encoding negative #1 ...[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] Denoising Strength = 1.0[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Parameters] Initial Latent shape: Image Space (1024, 1024)[0m
[32m[2024-04-12 09:35:00] INFO    [0m [34m[Fooocus] Preparation time: 0.69 seconds[0m
[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,  4.39it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.38it/s]
 10%|█         | 3/30 [00:00<00:06,  4.39it/s]
 13%|█▎        | 4/30 [00:00<00:05,  4.36it/s]
 17%|█▋        | 5/30 [00:01<00:05,  4.36it/s]
 20%|██        | 6/30 [00:01<00:05,  4.34it/s]
 23%|██▎       | 7/30 [00:01<00:05,  4.35it/s]
 27%|██▋       | 8/30 [00:01<00:05,  4.35it/s]
 30%|███       | 9/30 [00:02<00:04,  4.35it/s]
 33%|███▎      | 10/30 [00:02<00:04,  4.35it/s]
 37%|███▋      | 11/30 [00:02<00:04,  4.35it/s]
 40%|████      | 12/30 [00:02<00:04,  4.35it/s]
 43%|████▎     | 13/30 [00:02<00:03,  4.36it/s]
 47%|████▋     | 14/30 [00:03<00:03,  4.35it/s]
 50%|█████     | 15/30 [00:03<00:03,  4.35it/s]
 53%|█████▎    | 16/30 [00:03<00:03,  4.35it/s]
 57%|█████▋    | 17/30 [00:03<00:02,  4.35it/s]
 60%|██████    | 18/30 [00:04<00:02,  4.34it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  4.35it/s]
 67%|██████▋   | 20/30 [00:04<00:02,  4.34it/s]
 70%|███████   | 21/30 [00:04<00:02,  4.35it/s]
 73%|███████▎  | 22/30 [00:05<00:01,  4.35it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  4.35it/s]
 80%|████████  | 24/30 [00:05<00:01,  4.35it/s]
 83%|████████▎ | 25/30 [00:05<00:01,  4.35it/s]
 87%|████████▋ | 26/30 [00:05<00:00,  4.36it/s]
 90%|█████████ | 27/30 [00:06<00:00,  4.36it/s]
 93%|█████████▎| 28/30 [00:06<00:00,  4.36it/s]
 97%|█████████▋| 29/30 [00:06<00:00,  4.37it/s]
100%|██████████| 30/30 [00:06<00:00,  4.39it/s]
100%|██████████| 30/30 [00:06<00:00,  4.36it/s]
[32m[2024-04-12 09:35:07] INFO    [0m [34m[Fooocus] Generating and saving time: 7.12 seconds[0m
[32m[2024-04-12 09:35:09] INFO    [0m [34m[Task Queue] Finish task, job_id=3d589dae-0a96-4347-b017-b064ff961474[0m
[Predictor Predict] Finished with 1 images

Version Details

Version ID: 7c662db7ec7f06095f494c152e3de69084249385e12c2224bdcb6178a650d7c8
Version Created: January 13, 2025

Run on Replicate →