zust-ai/zust-diffusion 📝🔢✓ → 🖼️

▶️ 61.8K runs 📅 May 2023 ⚙️ Cog 0.8.6
image-editing image-to-image product-photography

About

auto1111_ds8

Example Output

Performance Metrics

10.39s Prediction Time
10.36s Total Time
Input Parameters
tags Type: stringDefault:
Product Tags (jewellery, topdown)
width Type: integerDefault: 1024
Width
height Type: integerDefault: 1024
height
pikeya Type: stringDefault:
Request Type
prompt Type: stringDefault: a handbag on a sofa in a sunlit living room with a bookshelf, plush rug, and a framed painting on the wall
Prompt
sam_url Type: stringDefault: {"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png"}
Get SAM Embeddings
subjects Type: stringDefault: [{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/zust_product/handbag_square.png"}]
Subject positions & URLs
pipe_type Type: stringDefault: zust_xl
SAM, photoshift, zust_fashion, zust_xl, upscale, enhance, cleanup
is_premium Type: booleanDefault: false
Is this a pro user?
upscale_by Type: integerDefault: 2
Upscaling factor
hires_noise Type: numberDefault: 0.55
Noise strength for hires.fix
upscale_url Type: stringDefault: {"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png"}
Upscale the Image
with_detail Type: booleanDefault: false
Detailed Output
cleanup_data Type: stringDefault: {"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png", "mask": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene_subject2.png"}
Image URL to be cleaned
fashion_mask Type: stringDefault: {"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/zust_fashion/fashion_sq_mask.png"}
Fashihon pose
is_heartbeat Type: booleanDefault: false
Check if Server Alive
enhance_noise Type: numberDefault: 0.5
Noise to be added in the scene
enhance_scene Type: stringDefault: {"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/enhance/scene_to_be_enhanced.png"}
Scene to be enhanced
enhance_prompt Type: stringDefault:
Enhanced Prompt
enhance_subject Type: stringDefault: [{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/enhance/enhance_sub.png"}]
Subject data (this shouldn't change)
fashion_subject Type: stringDefault: {"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/zust_fashion/fashion_sq.png"}
Subject positions & URLs
negative_prompt Type: stringDefault:
Negative Prompt
photoshift_noise Type: numberDefault: 0.65
Add noise to masked area
photoshift_scene Type: stringDefault: {"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png"}
Photoshift scene image
controlnet_weight Type: numberDefault: 0.8
Controlnet weight for the firstpass
enhance_reference Type: numberDefault: 0.25
IP-Adapter strength of scene. If 0 no Reference
photoshift_prompt Type: stringDefault:
Photoshift prompt
photoshift_resize Type: booleanDefault: true
PhotoShift (If resize the scene image)
photoshift_subject Type: stringDefault: [{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_raw2.png"}]
Photoshift subject(s) image
hires_guidance_scale Type: numberDefault: 5
Prompt strength for inpaint.fix
photoshift_reference Type: numberDefault: 0.35
IP-Adapter reference scale
enhance_negative_prompt Type: stringDefault:
Negative Prompt
photoshift_scene_subject Type: stringDefault:
Photoshift scene subject(s) image
photoshift_prompt_strength Type: numberDefault: 5
BLIP Caption strength
photoshift_cleanup_background Type: booleanDefault: true
PhotoShift (Clean source image subject)
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Version Details
Version ID
f545aeffe96a19a00079a23823af0d9260ca26f8795f54b1f21efe8c217827cd
Version Created
December 19, 2023
Run on Replicate →