tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- yarn
- art
widget:
- src: images/1.jpg
text: >-
[photo content], transformed into a crochet plush doll, with visible yarn
stitches, button eyes, and cozy handmade charm.
prompt: >
[photo content], transformed into a crochet plush doll, with visible yarn
stitches, button eyes, and cozy handmade charm.
output:
url: images/2.webp
base_model: black-forest-labs/FLUX.1-Kontext-dev
instance_prompt: >-
[photo content], transformed into a crochet plush doll, with visible yarn
stitches, button eyes, and cozy handmade charm.
license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE.md
pipeline_tag: image-to-image
Yarn-Photo-i2i [Image-to-Image]
- Prompt
- [photo content], transformed into a crochet plush doll, with visible yarn stitches, button eyes, and cozy handmade charm.
Yarn-Photo-i2i is an adapter for black-forest-lab's FLUX.1-Kontext-dev, designed for converting images into yarn-stitched artwork while preserving the original characteristics of the subject. The model was trained on 28 image pairs (14 start images, 14 end images). Synthetic result nodes were generated using NanoBanana from Google and SeedDream 4 (dataset for result sets), and labeled with DeepCaption-VLA-7B. The adapter is triggered with the following prompt:
[photo content], transformed into a crochet plush doll, with visible yarn stitches, button eyes, and cozy handmade charm.
Sample Inference
| ex1 | ex2 |
|---|---|
 |
 |
Parameter Settings
| Setting | Value |
|---|---|
| Module Type | Adapter |
| Base Model | FLUX.1 Kontext Dev - fp8 |
| Trigger Words | [photo content], transformed into a crochet plush doll, with visible yarn stitches, button eyes, and cozy handmade charm. |
| Image Processing Repeats | 50 |
| Epochs | 22 |
| Save Every N Epochs | 1 |
Labeling: DeepCaption-VLA-7B(natural language & English)
Total Images Used for Training : 28 Image Pairs (14 Start, 14 End)
Synthetic Result Node generated by NanoBanana from Google (Image Result Sets Dataset)
Training Parameters
| Setting | Value |
|---|---|
| Seed | - |
| Clip Skip | - |
| Text Encoder LR | 0.00001 |
| UNet LR | 0.00005 |
| LR Scheduler | constant |
| Optimizer | AdamW8bit |
| Network Dimension | 64 |
| Network Alpha | 32 |
| Gradient Accumulation Steps | - |
Label Parameters
| Setting | Value |
|---|---|
| Shuffle Caption | - |
| Keep N Tokens | - |
Advanced Parameters
| Setting | Value |
|---|---|
| Noise Offset | 0.03 |
| Multires Noise Discount | 0.1 |
| Multires Noise Iterations | 10 |
| Conv Dimension | - |
| Conv Alpha | - |
| Batch Size | - |
| Steps | 2900 |
| Sampler | euler |
Trigger words
You should use [photo content] to trigger the image generation.
You should use transformed into a crochet plush doll to trigger the image generation.
You should use with visible yarn stitches to trigger the image generation.
You should use button eyes to trigger the image generation.
You should use and cozy handmade charm. to trigger the image generation.
Download model
Download them in the Files & versions tab.