Image-to-Image
Diffusers
Safetensors
Diffusion Single File
English
Flux2KleinPipeline
text-to-image
image-editing
flux
Instructions to use YuCollection/FLUX.2-klein-base-4B-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use YuCollection/FLUX.2-klein-base-4B-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("YuCollection/FLUX.2-klein-base-4B-Diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Diffusion Single File
How to use YuCollection/FLUX.2-klein-base-4B-Diffusers with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Upload transformer/config.json with huggingface_hub
Browse files- transformer/config.json +24 -0
transformer/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "Flux2Transformer2DModel",
|
| 3 |
+
"_diffusers_version": "0.37.0.dev0",
|
| 4 |
+
"_name_or_path": "/raid/yiyi/klein-4b-diffusers/transformer",
|
| 5 |
+
"attention_head_dim": 128,
|
| 6 |
+
"axes_dims_rope": [
|
| 7 |
+
32,
|
| 8 |
+
32,
|
| 9 |
+
32,
|
| 10 |
+
32
|
| 11 |
+
],
|
| 12 |
+
"eps": 1e-06,
|
| 13 |
+
"guidance_embeds": false,
|
| 14 |
+
"in_channels": 128,
|
| 15 |
+
"joint_attention_dim": 7680,
|
| 16 |
+
"mlp_ratio": 3.0,
|
| 17 |
+
"num_attention_heads": 24,
|
| 18 |
+
"num_layers": 5,
|
| 19 |
+
"num_single_layers": 20,
|
| 20 |
+
"out_channels": null,
|
| 21 |
+
"patch_size": 1,
|
| 22 |
+
"rope_theta": 2000,
|
| 23 |
+
"timestep_guidance_channels": 256
|
| 24 |
+
}
|