alexgenovese/custom-endpoint 📝🖼️🔢❓ → 🖼️

▶️ 2.9K runs 📅 Nov 2023 ⚙️ Cog 0.8.6 🔗 GitHub ⚖️ License
image-inpainting image-to-image text-to-image

About

Fooocus API based endpoint

Example Output

Prompt:

"a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))"

Output

Example output

Performance Metrics

19.66s Prediction Time
19.69s Total Time
All Input Parameters
{
  "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))",
  "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": 4,
  "refiner_switch": 0.5,
  "negative_prompt": "",
  "style_selections": "Fooocus V2,Fooocus Enhance,Fooocus Sharp, Fooocus Photograph",
  "outpaint_selections": "",
  "performance_selection": "Quality",
  "aspect_ratios_selection": "1152×896"
}
Input Parameters
prompt Type: stringDefault:
Prompt for image generation
cn_img1 Type: string
Input image for image prompt (img2img). 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
lora_url Type: string
Lora url - Not Activated yet
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
image_number Type: integerDefault: 1Range: 1 - 8
How many image to generate
guidance_scale Type: numberDefault: 4Range: 1 - 30
refiner_switch Type: numberDefault: 0.5Range: 0.1 - 1
negative_prompt Type: stringDefault:
Negtive prompt for image generation
uov_input_image Type: string
Input image for upscale or variation, keep None for not upscale or variation
style_selections Type: stringDefault: Fooocus V2,Fooocus Enhance,Fooocus Sharp,Fooocus Photograph
Fooocus styles applied for image generation, seperated by comma
inpaint_input_mask Type: string
Input mask for inpaint
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' seperated by comma
performance_selection Default: Speed
Performance selection
aspect_ratios_selection Default: 1152×896
The generated image's size
inpaint_additional_prompt Type: string
additional prompt
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
[Predictor Predict] Params: {'prompt': 'a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))', 'negative_prompt': '', 'style_selections': ['Fooocus V2', 'Fooocus Enhance', 'Fooocus Sharp', 'Fooocus Photograph'], 'performance_selection': 'Quality', 'aspect_ratios_selection': '1152×896', 'image_number': 1, 'image_seed': -1, 'sharpness': 2.0, 'guidance_scale': 4.0, 'base_model_name': 'juggernautXL_version6Rundiffusion.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', 'outpaint_selections': [], 'inpaint_input_image': None, 'inpaint_additional_prompt': None, '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=4
[Parameters] Adaptive CFG = 7.0
[Parameters] Sharpness = 2.0
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] CFG = 4.0
[Parameters] Seed = 8354465421749182772
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 60 - 30
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
[Prompt Expansion] a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view)), elegant, highly detailed, extremely sharp focus, cinematic color, rich deep colors, intricate, very artistic, appealing, magical atmosphere, iconic
[Fooocus] Encoding positive #1 ...
[Fooocus] Encoding negative #1 ...
[Parameters] Denoising Strength = 1.0
[Parameters] Initial Latent shape: Image Space (896, 1152)
Preparation time: 0.60 seconds
[Sampler] refiner_swap_method = joint
[Sampler] sigma_min = 0.0291671771556139, sigma_max = 14.614643096923828
Requested to load SDXL
Loading 1 new model
[Fooocus Model Management] Moving model(s) has taken 1.27 seconds
  0%|          | 0/60 [00:00<?, ?it/s]
  2%|▏         | 1/60 [00:00<00:15,  3.93it/s]
  3%|▎         | 2/60 [00:00<00:14,  3.92it/s]
  5%|▌         | 3/60 [00:00<00:14,  3.92it/s]
  7%|▋         | 4/60 [00:01<00:14,  3.92it/s]
  8%|▊         | 5/60 [00:01<00:14,  3.91it/s]
 10%|█         | 6/60 [00:01<00:13,  3.91it/s]
 12%|█▏        | 7/60 [00:01<00:13,  3.91it/s]
 13%|█▎        | 8/60 [00:02<00:13,  3.91it/s]
 15%|█▌        | 9/60 [00:02<00:13,  3.91it/s]
 17%|█▋        | 10/60 [00:02<00:12,  3.90it/s]
 18%|█▊        | 11/60 [00:02<00:12,  3.91it/s]
 20%|██        | 12/60 [00:03<00:12,  3.90it/s]
 22%|██▏       | 13/60 [00:03<00:12,  3.90it/s]
 23%|██▎       | 14/60 [00:03<00:11,  3.90it/s]
 25%|██▌       | 15/60 [00:03<00:11,  3.90it/s]
 27%|██▋       | 16/60 [00:04<00:11,  3.90it/s]
 28%|██▊       | 17/60 [00:04<00:11,  3.90it/s]
 30%|███       | 18/60 [00:04<00:10,  3.90it/s]
 32%|███▏      | 19/60 [00:04<00:10,  3.87it/s]
 33%|███▎      | 20/60 [00:05<00:10,  3.88it/s]
 35%|███▌      | 21/60 [00:05<00:10,  3.88it/s]
 37%|███▋      | 22/60 [00:05<00:09,  3.89it/s]
 38%|███▊      | 23/60 [00:05<00:09,  3.89it/s]
 40%|████      | 24/60 [00:06<00:09,  3.89it/s]
 42%|████▏     | 25/60 [00:06<00:08,  3.89it/s]
 43%|████▎     | 26/60 [00:06<00:08,  3.88it/s]
 45%|████▌     | 27/60 [00:06<00:08,  3.89it/s]
 47%|████▋     | 28/60 [00:07<00:08,  3.89it/s]
 48%|████▊     | 29/60 [00:07<00:07,  3.88it/s]
 50%|█████     | 30/60 [00:07<00:07,  3.89it/s]
 52%|█████▏    | 31/60 [00:07<00:07,  3.88it/s]
 53%|█████▎    | 32/60 [00:08<00:07,  3.88it/s]
 55%|█████▌    | 33/60 [00:08<00:06,  3.88it/s]
 57%|█████▋    | 34/60 [00:08<00:06,  3.89it/s]
 58%|█████▊    | 35/60 [00:08<00:06,  3.89it/s]
 60%|██████    | 36/60 [00:09<00:06,  3.88it/s]
 62%|██████▏   | 37/60 [00:09<00:05,  3.89it/s]
 63%|██████▎   | 38/60 [00:09<00:05,  3.87it/s]
 65%|██████▌   | 39/60 [00:10<00:05,  3.87it/s]
 67%|██████▋   | 40/60 [00:10<00:05,  3.87it/s]
 68%|██████▊   | 41/60 [00:10<00:04,  3.88it/s]
 70%|███████   | 42/60 [00:10<00:04,  3.88it/s]
 72%|███████▏  | 43/60 [00:11<00:04,  3.88it/s]
 73%|███████▎  | 44/60 [00:11<00:04,  3.88it/s]
 75%|███████▌  | 45/60 [00:11<00:03,  3.88it/s]
 77%|███████▋  | 46/60 [00:11<00:03,  3.87it/s]
 78%|███████▊  | 47/60 [00:12<00:03,  3.87it/s]
 80%|████████  | 48/60 [00:12<00:03,  3.87it/s]
 82%|████████▏ | 49/60 [00:12<00:02,  3.88it/s]
 83%|████████▎ | 50/60 [00:12<00:02,  3.88it/s]
 85%|████████▌ | 51/60 [00:13<00:02,  3.87it/s]
 87%|████████▋ | 52/60 [00:13<00:02,  3.88it/s]
 88%|████████▊ | 53/60 [00:13<00:01,  3.88it/s]
 90%|█████████ | 54/60 [00:13<00:01,  3.88it/s]
 92%|█████████▏| 55/60 [00:14<00:01,  3.88it/s]
 93%|█████████▎| 56/60 [00:14<00:01,  3.88it/s]
 95%|█████████▌| 57/60 [00:14<00:00,  3.87it/s]
 97%|█████████▋| 58/60 [00:14<00:00,  3.88it/s]
 98%|█████████▊| 59/60 [00:15<00:00,  3.88it/s]
100%|██████████| 60/60 [00:15<00:00,  3.90it/s]
100%|██████████| 60/60 [00:15<00:00,  3.89it/s]
Generating and saving time: 17.14 seconds
[Task Queue] Finish task, seq=4
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
[Fooocus Model Management] Moving model(s) has taken 0.40 seconds
[Predictor Predict] Finished with 1 images
Version Details
Version ID
9dab65ee74fff214a1de295299ba57eb8f4540be3c9839027d2a02f505989888
Version Created
November 24, 2023
Run on Replicate →