jinchanz/comfyui 🖼️📝✓ → ❓
About
Example Output
Output
{"files":["https://replicate.delivery/pbxt/6Ft2k1qx2nL5LZG1MJ39VTyZaKJwaWJDKxhwN5UMuIejSwdJA/ComfyUI_00001_.png"],"results":"{"60": {"images": [{"filename": "ComfyUI_temp_fhdaa_00001_.png", "subfolder": "", "type": "temp"}]}, "19": {"images": [{"filename": "ComfyUI_00001_.png", "subfolder": "", "type": "output"}]}}"}
Performance Metrics
34.79s
Prediction Time
152.51s
Total Time
All Input Parameters
{
"workflow_json": "{\"19\":{\"inputs\":{\"filename_prefix\":\"ComfyUI\",\"images\":[\"60\",5]},\"class_type\":\"SaveImage\",\"_meta\":{\"title\":\"Save Image\"}},\"60\":{\"inputs\":{\"seed\":508755962671027,\"steps\":25,\"cfg\":4,\"sampler_name\":\"dpmpp_2m_sde_gpu\",\"scheduler\":\"karras\",\"denoise\":1,\"preview_method\":\"auto\",\"vae_decode\":\"true\",\"sharpness\":2,\"model\":[\"61\",0],\"positive\":[\"61\",1],\"negative\":[\"61\",2],\"latent_image\":[\"61\",3],\"optional_vae\":[\"61\",4],\"script\":[\"64\",0]},\"class_type\":\"Fooocus_KSamplerEfficient\",\"_meta\":{\"title\":\"KSampler Efficient Fooocus\"}},\"61\":{\"inputs\":{\"ckpt_name\":\"ArcadeXL_v0.1.safetensors\",\"vae_name\":\"Baked VAE\",\"clip_skip\":-2,\"lora_name\":\"Arcade-Lora_v0.1.safetensors\",\"lora_model_strength\":0.25,\"lora_clip_strength\":1,\"positive\":\"architecture rendering, beautiful composition, scenery, best quality, ultra-detailed, high resolution, realistic photography with natural light and high contrast, cinematic 8k, architectural rendering, unreal engine 5, rtx, volumetric light, masterpiece\",\"negative\":\" (Easy Negtive:1.4), (worst quality: 1.4), (low quality:1.4), (normal quality:1.4), nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, messy, bad chair, bad machine, bad lighting_cigarette, \",\"token_normalization\":\"none\",\"weight_interpretation\":\"A1111\",\"empty_latent_width\":1344,\"empty_latent_height\":768,\"batch_size\":1},\"class_type\":\"Efficient Loader\",\"_meta\":{\"title\":\"Efficient Loader\"}},\"64\":{\"inputs\":{\"rng_source\":\"gpu\",\"cfg_denoiser\":false,\"add_seed_noise\":false,\"seed\":-1,\"weight\":0.015},\"class_type\":\"Noise Control Script\",\"_meta\":{\"title\":\"Noise Control Script\"}}}",
"randomise_seeds": true,
"return_temp_files": false
}
Input Parameters
- input_file
- Input image, tar or zip file. Read guidance on workflows and input files here: https://github.com/fofr/cog-comfyui. Alternatively, you can replace inputs with URLs in your JSON workflow and the model will download them.
- workflow_json
- Your ComfyUI workflow as JSON. You must use the API version of your workflow. Get it from ComfyUI using ‘Save (API format)’. Instructions here: https://github.com/fofr/cog-comfyui
- randomise_seeds
- Automatically randomise seeds (seed, noise_seed, rand_seed)
- return_temp_files
- Return any temporary files, such as preprocessed controlnet images. Useful for debugging.
Output Schema
- files
- Files
- results
- Results
Example Execution Logs
Checking inputs
====================================
Checking weights
⏳ Downloading ArcadeXL_v0.1.safetensors to ComfyUI/models/checkpoints
⌛️ Downloaded ArcadeXL_v0.1.safetensors in 21.18s, size: 6616.63MB
✅ ArcadeXL_v0.1.safetensors
⏳ Downloading Arcade-Lora_v0.1.safetensors to ComfyUI/models/loras
⌛️ Downloaded Arcade-Lora_v0.1.safetensors in 2.23s, size: 217.87MB
✅ Arcade-Lora_v0.1.safetensors
====================================
Randomising seed to 71942953
Randomising seed to 76262150
Running workflow
got prompt
[32m[rgthree] Using rgthree's optimized recursive execution.[0m
Executing node 61, title: Efficient Loader, class type: Efficient Loader
model_type EPS
Using pytorch attention in VAE
Using pytorch attention in VAE
Requested to load SDXLClipModel
Loading 1 new model
----------------------------------------
[36mEfficient Loader Models Cache:[0m
Ckpt:
[1] ArcadeXL_v0.1
Lora:
[1] base_ckpt: ArcadeXL_v0.1
lora(mod,clip): Arcade-Lora_v0.1(0.25,1.0)
Executing node 64, title: Noise Control Script, class type: Noise Control Script
Executing node 60, title: KSampler Efficient Fooocus, class type: Fooocus_KSamplerEfficient
Requested to load SDXL
Loading 1 new model
0%| | 0/25 [00:00<?, ?it/s]
4%|▍ | 1/25 [00:00<00:05, 4.59it/s]
8%|▊ | 2/25 [00:00<00:04, 4.92it/s]
12%|█▏ | 3/25 [00:00<00:04, 5.07it/s]
16%|█▌ | 4/25 [00:00<00:04, 5.13it/s]
20%|██ | 5/25 [00:00<00:03, 5.18it/s]
24%|██▍ | 6/25 [00:01<00:03, 5.21it/s]
28%|██▊ | 7/25 [00:01<00:03, 5.22it/s]
32%|███▏ | 8/25 [00:01<00:03, 5.22it/s]
36%|███▌ | 9/25 [00:01<00:03, 5.21it/s]
40%|████ | 10/25 [00:01<00:02, 5.21it/s]
44%|████▍ | 11/25 [00:02<00:02, 5.21it/s]
48%|████▊ | 12/25 [00:02<00:02, 5.22it/s]
52%|█████▏ | 13/25 [00:02<00:02, 5.22it/s]
56%|█████▌ | 14/25 [00:02<00:02, 5.22it/s]
60%|██████ | 15/25 [00:02<00:01, 5.22it/s]
64%|██████▍ | 16/25 [00:03<00:01, 5.22it/s]
68%|██████▊ | 17/25 [00:03<00:01, 5.23it/s]
72%|███████▏ | 18/25 [00:03<00:01, 5.23it/s]
76%|███████▌ | 19/25 [00:03<00:01, 5.22it/s]
80%|████████ | 20/25 [00:03<00:00, 5.23it/s]
84%|████████▍ | 21/25 [00:04<00:00, 5.24it/s]
88%|████████▊ | 22/25 [00:04<00:00, 5.24it/s]
92%|█████████▏| 23/25 [00:04<00:00, 5.25it/s]
96%|█████████▌| 24/25 [00:04<00:00, 5.29it/s]
100%|██████████| 25/25 [00:04<00:00, 5.33it/s]
100%|██████████| 25/25 [00:04<00:00, 5.22it/s]
Requested to load AutoencoderKL
Loading 1 new model
Executing node 19, title: Save Image, class type: SaveImage
Prompt executed in 9.71 seconds
outputs: {'60': {'images': [{'filename': 'ComfyUI_temp_fhdaa_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '19': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
Contents of /tmp/outputs:
ComfyUI_00001_.png
Version Details
- Version ID
979dc3e55b978038620d5a03f988b604c03a903f5784a4bc38017e9a88e3bc06- Version Created
- June 5, 2024