Instructions to use funseshon/midri with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use funseshon/midri with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Raw", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("funseshon/midri") prompt = "A futuristic cybernetic owl perched on a neon-lit skyscraper ledge in a rainy Tokyo alley, MIDRI cinematic lighting, 8k resolution." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
End of training
Browse files- README.md +75 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/pytorch_lora_weights.safetensors +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-500/optimizer.bin +3 -0
- checkpoint-500/pytorch_lora_weights.safetensors +3 -0
- checkpoint-500/random_states_0.pkl +3 -0
- checkpoint-500/scheduler.bin +3 -0
- pytorch_lora_weights.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- krea/Krea-2-Turbo
|
| 4 |
+
- krea/Krea-2-Raw
|
| 5 |
+
library_name: diffusers
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
instance_prompt: MIDRI
|
| 8 |
+
widget: []
|
| 9 |
+
tags:
|
| 10 |
+
- text-to-image
|
| 11 |
+
- diffusers-training
|
| 12 |
+
- diffusers
|
| 13 |
+
- lora
|
| 14 |
+
- krea2
|
| 15 |
+
- krea2-diffusers
|
| 16 |
+
- template:sd-lora
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
| 20 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
# Krea 2 DreamBooth LoRA - funseshon/midri
|
| 24 |
+
|
| 25 |
+
<Gallery />
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
These are funseshon/midri DreamBooth LoRA weights, trained on krea/Krea-2-Raw.
|
| 30 |
+
|
| 31 |
+
The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [Krea 2 diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_krea2.md).
|
| 32 |
+
|
| 33 |
+
Krea 2 ships as two checkpoints: **RAW** (the non-distilled base you fine-tune on) and **Turbo** (an 8-step distilled checkpoint for fast, high-quality inference). Train your LoRA on RAW and run it on Turbo — LoRAs trained on RAW express strongly on Turbo.
|
| 34 |
+
|
| 35 |
+
## Trigger words
|
| 36 |
+
|
| 37 |
+
You should use `MIDRI` to trigger the image generation.
|
| 38 |
+
|
| 39 |
+
## Download model
|
| 40 |
+
|
| 41 |
+
[Download the *.safetensors LoRA](funseshon/midri/tree/main) in the Files & versions tab.
|
| 42 |
+
|
| 43 |
+
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
|
| 44 |
+
|
| 45 |
+
```py
|
| 46 |
+
>>> import torch
|
| 47 |
+
>>> from diffusers import Krea2Pipeline
|
| 48 |
+
|
| 49 |
+
>>> # Load the LoRA onto Krea 2 Turbo (the distilled inference model)
|
| 50 |
+
>>> pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
|
| 51 |
+
>>> pipe.load_lora_weights("funseshon/midri")
|
| 52 |
+
|
| 53 |
+
>>> # Turbo recipe: 8 steps, no classifier-free guidance
|
| 54 |
+
>>> image = pipe("MIDRI", num_inference_steps=8, guidance_scale=0.0).images[0]
|
| 55 |
+
>>> image.save("output.png")
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
## Intended uses & limitations
|
| 62 |
+
|
| 63 |
+
#### How to use
|
| 64 |
+
|
| 65 |
+
```python
|
| 66 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
| 67 |
+
```
|
| 68 |
+
|
| 69 |
+
#### Limitations and bias
|
| 70 |
+
|
| 71 |
+
[TODO: provide examples of latent issues and potential remediations]
|
| 72 |
+
|
| 73 |
+
## Training details
|
| 74 |
+
|
| 75 |
+
[TODO: describe the data used to train the model]
|
checkpoint-1000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c887ccb34cd24f04ba31fdc648f3d3de47d259d7cca61ae2f642604a98f2c010
|
| 3 |
+
size 195389021
|
checkpoint-1000/pytorch_lora_weights.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:933683a59f170468219c852e1600f92db168c3285e4a2afd09e4c0e5f9f7beec
|
| 3 |
+
size 191879376
|
checkpoint-1000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3503fa41fdd93f77ed5cf9299998caf20659ba7bbe33f77f96b05111b67e2d9f
|
| 3 |
+
size 14757
|
checkpoint-1000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95d5da8195335d4ea322bbf2d1a3e2e6db077cf77404469c5cb95a451f7e56fa
|
| 3 |
+
size 1401
|
checkpoint-500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3e39139b87266403f04e77d4ea922832f9ac8c0c172b4922a4de444a13f21d0
|
| 3 |
+
size 195389021
|
checkpoint-500/pytorch_lora_weights.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dff082f130ab451c1417a5293921841ab718dbcef1ee70d30a39965232963176
|
| 3 |
+
size 191879376
|
checkpoint-500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d4332128030d2e70a6303e3b2ee9a3b49c99fc6636e55ecde408012f541f346
|
| 3 |
+
size 14757
|
checkpoint-500/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6b09a32f9bd8c3811caf53e7088f9d0094eade3af68c322a05eb696814b1a19
|
| 3 |
+
size 1401
|
pytorch_lora_weights.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:933683a59f170468219c852e1600f92db168c3285e4a2afd09e4c0e5f9f7beec
|
| 3 |
+
size 191879376
|