goodguy1963/hidream-l1-full-img2img 🔢🖼️❓📝✓ → 🖼️
About
IMG2IMG for HiDream FULL AND DEV - does creative variations

Example Output
Output

Performance Metrics
56.91s
Prediction Time
56.92s
Total Time
All Input Parameters
{ "cfg": 5, "seed": 42, "image": "https://replicate.delivery/pbxt/MtXvN5k7FNnb0dxuHFqRRKdhu2z4eqpxgpMANTOP6vUeNTSb/Better%20prompt%20%20%2813%29.jpeg", "steps": 50, "denoise": 0.6, "scheduler": "normal", "sampler_name": "uni_pc" }
Input Parameters
- cfg
- Guidance scale
- seed
- Random seed
- image
- Input image file (required)
- shift
- ModelSamplingSD3 shift parameter (0-20)
- steps
- Number of inference steps
- denoise
- Denoising strength
- scheduler
- Scheduler for the sampler
- sampler_name
- Sampling algorithm to use
- model_variant
- HiDream model variant to use
- prompt_prefix
- With Florence2: Prefix to add to generated caption. Without Florence2: Complete prompt to use
- use_florence2
- Use Florence2 for automatic caption generation
- florence2_task
- Florence2 task to perform
- negative_prompt
- Negative prompt to guide the model away from certain elements
- florence2_text_input
- Optional text input for Florence2 (only used when Florence2 is enabled)
Output Schema
Output
Example Execution Logs
📦 Downloading required HiDream models... Total models to check: 6 🔄 Processing model 1/6: hidream_i1_full_fp16.safetensors ✅ Model hidream_i1_full_fp16.safetensors already exists (31.86 GB), skipping download 🔄 Processing model 2/6: clip_g_hidream.safetensors ✅ Model clip_g_hidream.safetensors already exists (1.29 GB), skipping download 🔄 Processing model 3/6: clip_l_hidream.safetensors ✅ Model clip_l_hidream.safetensors already exists (236.1 MB), skipping download 🔄 Processing model 4/6: llama_3.1_8b_instruct_fp8_scaled.safetensors ✅ Model llama_3.1_8b_instruct_fp8_scaled.safetensors already exists (8.46 GB), skipping download 🔄 Processing model 5/6: t5xxl_fp8_e4m3fn_scaled.safetensors ✅ Model t5xxl_fp8_e4m3fn_scaled.safetensors already exists (4.80 GB), skipping download 🔄 Processing model 6/6: ae.safetensors ✅ Model ae.safetensors already exists (319.8 MB), skipping download 📊 Download Summary: ✅ Successfully downloaded/verified: 6/6 Models ready: - hidream_i1_full_fp16.safetensors (31.86 GB) - clip_g_hidream.safetensors (1.29 GB) - clip_l_hidream.safetensors (236.1 MB) - llama_3.1_8b_instruct_fp8_scaled.safetensors (8.46 GB) - t5xxl_fp8_e4m3fn_scaled.safetensors (4.80 GB) - ae.safetensors (319.8 MB) Seed set to: 42 Running workflow [ComfyUI] got prompt Executing node 108, title: String Function 🐍, class type: StringFunction|pysssss Executing node 16, title: Positive Prompt, class type: CLIPTextEncode Executing node 3, title: KSampler, class type: KSampler [ComfyUI] [ComfyUI] 0%| | 0/50 [00:00<?, ?it/s] [ComfyUI] 2%|▏ | 1/50 [00:01<00:53, 1.09s/it] [ComfyUI] 4%|▍ | 2/50 [00:02<00:52, 1.10s/it] [ComfyUI] 6%|▌ | 3/50 [00:03<00:51, 1.10s/it] [ComfyUI] 8%|▊ | 4/50 [00:04<00:50, 1.10s/it] [ComfyUI] 10%|█ | 5/50 [00:05<00:49, 1.10s/it] [ComfyUI] 12%|█▏ | 6/50 [00:06<00:48, 1.10s/it] [ComfyUI] 14%|█▍ | 7/50 [00:07<00:47, 1.10s/it] [ComfyUI] 16%|█▌ | 8/50 [00:08<00:46, 1.10s/it] [ComfyUI] 18%|█▊ | 9/50 [00:09<00:45, 1.10s/it] [ComfyUI] 20%|██ | 10/50 [00:11<00:44, 1.10s/it] [ComfyUI] 22%|██▏ | 11/50 [00:12<00:43, 1.10s/it] [ComfyUI] 24%|██▍ | 12/50 [00:13<00:41, 1.10s/it] [ComfyUI] 26%|██▌ | 13/50 [00:14<00:40, 1.10s/it] [ComfyUI] 28%|██▊ | 14/50 [00:15<00:39, 1.10s/it] [ComfyUI] 30%|███ | 15/50 [00:16<00:38, 1.10s/it] [ComfyUI] 32%|███▏ | 16/50 [00:17<00:37, 1.10s/it] [ComfyUI] 34%|███▍ | 17/50 [00:18<00:36, 1.10s/it] [ComfyUI] 36%|███▌ | 18/50 [00:19<00:35, 1.11s/it] [ComfyUI] 38%|███▊ | 19/50 [00:20<00:34, 1.11s/it] [ComfyUI] 40%|████ | 20/50 [00:22<00:33, 1.11s/it] [ComfyUI] 42%|████▏ | 21/50 [00:23<00:32, 1.11s/it] [ComfyUI] 44%|████▍ | 22/50 [00:24<00:30, 1.11s/it] [ComfyUI] 46%|████▌ | 23/50 [00:25<00:29, 1.11s/it] [ComfyUI] 48%|████▊ | 24/50 [00:26<00:28, 1.11s/it] [ComfyUI] 50%|█████ | 25/50 [00:27<00:27, 1.11s/it] [ComfyUI] 52%|█████▏ | 26/50 [00:28<00:26, 1.11s/it] [ComfyUI] 54%|█████▍ | 27/50 [00:29<00:25, 1.11s/it] [ComfyUI] 56%|█████▌ | 28/50 [00:30<00:24, 1.11s/it] [ComfyUI] 58%|█████▊ | 29/50 [00:32<00:23, 1.11s/it] [ComfyUI] 60%|██████ | 30/50 [00:33<00:22, 1.11s/it] [ComfyUI] 62%|██████▏ | 31/50 [00:34<00:21, 1.11s/it] [ComfyUI] 64%|██████▍ | 32/50 [00:35<00:19, 1.11s/it] [ComfyUI] 66%|██████▌ | 33/50 [00:36<00:18, 1.11s/it] [ComfyUI] 68%|██████▊ | 34/50 [00:37<00:17, 1.11s/it] [ComfyUI] 70%|███████ | 35/50 [00:38<00:16, 1.11s/it] [ComfyUI] 72%|███████▏ | 36/50 [00:39<00:15, 1.11s/it] [ComfyUI] 74%|███████▍ | 37/50 [00:40<00:14, 1.11s/it] [ComfyUI] 76%|███████▌ | 38/50 [00:41<00:13, 1.11s/it] [ComfyUI] 78%|███████▊ | 39/50 [00:43<00:12, 1.11s/it] [ComfyUI] 80%|████████ | 40/50 [00:44<00:11, 1.11s/it] [ComfyUI] 82%|████████▏ | 41/50 [00:45<00:09, 1.11s/it] [ComfyUI] 84%|████████▍ | 42/50 [00:46<00:08, 1.11s/it] [ComfyUI] 86%|████████▌ | 43/50 [00:47<00:07, 1.11s/it] [ComfyUI] 88%|████████▊ | 44/50 [00:48<00:06, 1.11s/it] [ComfyUI] 90%|█████████ | 45/50 [00:49<00:05, 1.11s/it] [ComfyUI] 92%|█████████▏| 46/50 [00:50<00:04, 1.11s/it] [ComfyUI] 94%|█████████▍| 47/50 [00:51<00:03, 1.11s/it] [ComfyUI] 96%|█████████▌| 48/50 [00:53<00:02, 1.11s/it] [ComfyUI] 98%|█████████▊| 49/50 [00:54<00:01, 1.11s/it] [ComfyUI] 100%|██████████| 50/50 [00:55<00:00, 1.11s/it] Executing node 8, title: VAE Decode, class type: VAEDecode Executing node 9, title: Save Image, class type: SaveImage [ComfyUI] 100%|██████████| 50/50 [00:55<00:00, 1.11s/it] [ComfyUI] Prompt executed in 56.19 seconds outputs: {'108': {'text': ['Photo, A photo-realistic shoot from a front camera angle about a young woman sitting at a wooden table with a small dog in a cozy indoor setting. the image also shows a warm and inviting atmosphere. on the middle of the image, a 20 years old woman with light brown hair and blue eyes appears to be looking directly at the viewer. she is wearing a beige long-sleeved sweater and has a gentle smile on her face. her hands are resting on her chin, and she is sitting at the wooden table in front of the small dog. the dog is a small, fluffy breed with a brown and white coat. the background features a cozy living room with wooden beams and large windows letting in natural light. the lighting is soft and warm, creating a cozy atmosphere. 1girl, looking at viewer, smile, blue eyes, long hair, blonde hair, animal, indoors, sweater, blurry, lips, blurry background, table, hands on own face, nose, realistic camera_angle: from front, art_style: photo realistic, location: indoor, background: A cozy room with large windows allowing natural light to enter, text: NA, distance_to_camera: upper body, clothing: beige oversized sweater, image_composition: middle, pants: NA']}, '9': {'images': [{'filename': 'ComfyUI-HiDream_00001_.png', 'subfolder': '', 'type': 'output'}]}} ==================================== ComfyUI-HiDream_00001_.png
Version Details
- Version ID
7820b5b85ecffa68a2ad8aeba3dfe526f1046fcaa209863fdcd999480751fc88
- Version Created
- April 25, 2025