noahgsolomon/yumemono 🔢📝❓ → 🖼️

▶️ 153 runs 📅 Mar 2025 ⚙️ Cog 0.14.3
anime lora text-to-image

About

YUMEMONO

Example Output

Prompt:

"Yumemono style, pixelated anime girl with short light blue hair and white flower crown, pale skin, large bright blue eyes, gentle smile, wearing black and white maid outfit with frilly details and purple ribbon hair accessory, against a spring background with pink cherry blossom trees, clear blue sky, and distant buildings."

Output

Example output

Performance Metrics

17.15s Prediction Time
17.16s Total Time
All Input Parameters
{
  "steps": 30,
  "prompt": "Yumemono style, pixelated anime girl with short light blue hair and white flower crown, pale skin, large bright blue eyes, gentle smile, wearing black and white maid outfit with frilly details and purple ribbon hair accessory, against a spring background with pink cherry blossom trees, clear blue sky, and distant buildings.",
  "denoise": 1,
  "guidance": 3.5,
  "aspect_ratio": "1:1 (Perfect Square)",
  "lora_strength": 1,
  "output_format": "webp",
  "output_quality": 95
}
Input Parameters
seed Type: integer
Set a seed for reproducibility. Random by default.
steps Type: integerDefault: 30Range: 10 - 100
Number of sampling steps
prompt Type: stringDefault: Yumemono style, cosmic deity with flowing hair
Describe what you want to generate
denoise Type: numberDefault: 1Range: 0 - 1
Denoising strength
guidance Type: numberDefault: 3.5Range: 1 - 10
Flux guidance scale
aspect_ratio Default: 2:3 (Classic Portrait)
Aspect ratio for the generated image
lora_strength Type: numberDefault: 1Range: 0 - 1
Strength of the Yumemono LoRA effect
output_format Default: webp
Format of the output images
output_quality Type: integerDefault: 95Range: 0 - 100
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Random seed set to: 1320448579
Checking inputs
====================================
Checking weights
✅ flux1-dev.safetensors exists in ComfyUI/models/diffusion_models
✅ t5xxl_fp16.safetensors exists in ComfyUI/models/text_encoders
✅ clip_l.safetensors exists in ComfyUI/models/text_encoders
✅ ae.safetensors exists in ComfyUI/models/vae
====================================
Running workflow
[ComfyUI] got prompt
Executing node 8, title: Flux Resolution Calc, class type: FluxResolutionNode
Executing node 6, title: Load VAE, class type: VAELoader
[ComfyUI] Using pytorch attention in VAE
[ComfyUI] Using pytorch attention in VAE
[ComfyUI] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Executing node 9, title: EmptySD3LatentImage, class type: EmptySD3LatentImage
Executing node 5, title: DualCLIPLoader, class type: DualCLIPLoader
[ComfyUI] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[ComfyUI] clip missing: ['text_projection.weight']
Executing node 4, title: Load Diffusion Model, class type: UNETLoader
[ComfyUI] model weight dtype torch.bfloat16, manual cast: None
[ComfyUI] model_type FLUX
Executing node 1, title: Load LoRA, class type: LoraLoaderFromURL
[ComfyUI] Requested to load FluxClipModel_
Executing node 12, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
[ComfyUI] loaded completely 79408.425 9319.23095703125 True
Executing node 11, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 10, title: FluxGuidance, class type: FluxGuidance
Executing node 7, title: KSampler, class type: KSampler
[ComfyUI] Requested to load Flux
[ComfyUI] loaded completely 69975.06891708374 22700.134887695312 True
[ComfyUI] ### Loading: ComfyUI-Impact-Pack (Subpack: V0.6)
[ComfyUI] [WARN] ComfyUI-Impact-Pack: `ComfyUI` or `ComfyUI-Manager` is an outdated version.
[ComfyUI] [Impact Pack] Wildcards loading done.
[ComfyUI] [ComfyUI]
[ComfyUI] Initializing ControlAltAI Nodes
[ComfyUI] Creating huggingface_cache directory within comfy
[ComfyUI] 0%|          | 0/30 [00:00<?, ?it/s]
[ComfyUI] 3%|▎         | 1/30 [00:00<00:07,  3.80it/s]
[ComfyUI] 7%|▋         | 2/30 [00:00<00:08,  3.49it/s]
[ComfyUI] 10%|█         | 3/30 [00:00<00:06,  3.94it/s]
[ComfyUI] 13%|█▎        | 4/30 [00:00<00:06,  4.18it/s]
[ComfyUI] 17%|█▋        | 5/30 [00:01<00:05,  4.33it/s]
[ComfyUI] 20%|██        | 6/30 [00:01<00:05,  4.43it/s]
[ComfyUI] 23%|██▎       | 7/30 [00:01<00:05,  4.49it/s]
[ComfyUI] 27%|██▋       | 8/30 [00:01<00:04,  4.53it/s]
[ComfyUI] 30%|███       | 9/30 [00:02<00:04,  4.55it/s]
[ComfyUI] 33%|███▎      | 10/30 [00:02<00:04,  4.57it/s]
[ComfyUI] 37%|███▋      | 11/30 [00:02<00:04,  4.59it/s]
[ComfyUI] 40%|████      | 12/30 [00:02<00:03,  4.59it/s]
[ComfyUI] 43%|████▎     | 13/30 [00:02<00:03,  4.60it/s]
[ComfyUI] 47%|████▋     | 14/30 [00:03<00:03,  4.61it/s]
[ComfyUI] 50%|█████     | 15/30 [00:03<00:03,  4.61it/s]
[ComfyUI] 53%|█████▎    | 16/30 [00:03<00:03,  4.61it/s]
[ComfyUI] 57%|█████▋    | 17/30 [00:03<00:02,  4.62it/s]
[ComfyUI] 60%|██████    | 18/30 [00:04<00:02,  4.61it/s]
[ComfyUI] 63%|██████▎   | 19/30 [00:04<00:02,  4.61it/s]
[ComfyUI] 67%|██████▋   | 20/30 [00:04<00:02,  4.62it/s]
[ComfyUI] 70%|███████   | 21/30 [00:04<00:01,  4.62it/s]
[ComfyUI] 73%|███████▎  | 22/30 [00:04<00:01,  4.62it/s]
[ComfyUI] 77%|███████▋  | 23/30 [00:05<00:01,  4.62it/s]
[ComfyUI] 80%|████████  | 24/30 [00:05<00:01,  4.62it/s]
[ComfyUI] 83%|████████▎ | 25/30 [00:05<00:01,  4.62it/s]
[ComfyUI] 87%|████████▋ | 26/30 [00:05<00:00,  4.62it/s]
[ComfyUI] 90%|█████████ | 27/30 [00:05<00:00,  4.62it/s]
[ComfyUI] 93%|█████████▎| 28/30 [00:06<00:00,  4.62it/s]
[ComfyUI] 97%|█████████▋| 29/30 [00:06<00:00,  4.49it/s]
[ComfyUI] 100%|██████████| 30/30 [00:06<00:00,  4.53it/s]
[ComfyUI] 100%|██████████| 30/30 [00:06<00:00,  4.51it/s]
[ComfyUI] Requested to load AutoencodingEngine
Executing node 13, title: VAE Decode, class type: VAEDecode
[ComfyUI] loaded completely 46027.20537567139 159.87335777282715 True
Executing node 14, title: Save Image, class type: SaveImage
[ComfyUI] Prompt executed in 16.84 seconds
outputs:  {'14': {'images': [{'filename': 'output_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
output_00001_.png
Version Details
Version ID
e4f38e7a01f7150fcd8264b9af728b6fd5f0ce41b487ada9f0ab85b9a49b323f
Version Created
March 26, 2025
Run on Replicate →