multimodalart HF staff commited on
Commit
28dd741
1 Parent(s): c2db27b

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - text-to-image
4
+ - flux
5
+ - lora
6
+ - diffusers
7
+ - template:sd-lora
8
+ - ai-toolkit
9
+ widget:
10
+ - text: A person in a bustling cafe in the style of tarsila do amaral
11
+ output:
12
+ url: samples/1725254450130__000001000_0.jpg
13
+ - text: A mecha robot in a favela in the style of tarsila do amaral
14
+ output:
15
+ url: samples/1725254552381__000001000_1.jpg
16
+ base_model: black-forest-labs/FLUX.1-dev
17
+ instance_prompt: in the style of tarsila do amaral
18
+ license: other
19
+ license_name: flux-1-dev-non-commercial-license
20
+ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
21
+ ---
22
+
23
+ # tarsila-captioned
24
+ Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
25
+ <Gallery />
26
+
27
+ ## Trigger words
28
+
29
+ You should use `in the style of tarsila do amaral` to trigger the image generation.
30
+
31
+ ## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
32
+
33
+ Weights for this model are available in Safetensors format.
34
+
35
+ [Download](/multimodalart/tarsila-captioned/tree/main) them in the Files & versions tab.
36
+
37
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
38
+
39
+ ```py
40
+ from diffusers import AutoPipelineForText2Image
41
+ import torch
42
+
43
+ pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
44
+ pipeline.load_lora_weights('multimodalart/tarsila-captioned', weight_name='tarsila-captioned')
45
+ image = pipeline('A person in a bustling cafe in the style of tarsila do amaral').images[0]
46
+ image.save("my_image.png")
47
+ ```
48
+
49
+ 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)
50
+
samples/1725254450130__000001000_0.jpg ADDED
samples/1725254552381__000001000_1.jpg ADDED
tarsila-captioned.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e3a69dc2d8679ed07f870f28581f936838ef55d16c4b7851dfc73151373864
3
+ size 171969464