Duplicate from fffiloni/sd-img-variations

Co-authored-by: Sylvain Filoni <[email protected]>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Stable Diffusion Img Variations CPU
+emoji: 🐓🐣🐣🐣🐣
+colorFrom: red
+colorTo: pink
+sdk: gradio
+sdk_version: 3.3.1
+app_file: app.py
+pinned: false
+duplicated_from: fffiloni/sd-img-variations
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,87 @@
+import gradio as gr
+import torch
+from PIL import Image
+
+from lambda_diffusers import StableDiffusionImageEmbedPipeline
+
+def ask(input_im, scale, steps, seed, images):
+    images = images
+    generator = torch.Generator(device=device).manual_seed(int(seed))
+    
+    images_list = pipe(
+        2*[input_im],
+        guidance_scale=scale,
+        num_inference_steps=steps,
+        generator=generator,
+        )
+    
+    for i, image in enumerate(images_list["sample"]):
+        if(images_list["nsfw_content_detected"][i]):
+            safe_image = Image.open(r"unsafe.png")
+            images.append(safe_image)
+        else:
+            images.append(image)
+    return images
+
+def main(input_im, n_pairs, scale, steps, seed):
+    print('Start the magic !')
+    images = []
+    for i in range(n_pairs):
+        print('Asking for a new pair of image [' + str(i + 1) + '/' + str(n_pairs) + ']')
+        seed = seed+i
+        images = ask(input_im, scale, steps, seed, images)
+    print('Thanks to Sylvain, it worked like a charm!')
+    return images
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+pipe = StableDiffusionImageEmbedPipeline.from_pretrained(
+    "lambdalabs/sd-image-variations-diffusers",
+    revision="273115e88df42350019ef4d628265b8c29ef4af5",
+    )
+pipe = pipe.to(device)
+
+inputs = [
+    gr.Image(),
+    gr.Slider(1, 3, value=2, step=1, label="Pairs of images to ask"),
+    gr.Slider(0, 25, value=3, step=1, label="Guidance scale"),
+    gr.Slider(5, 50, value=25, step=5, label="Steps"),
+    gr.Slider(label = "Seed", minimum = 0, maximum = 2147483647, step = 1, randomize = True)
+]
+output = gr.Gallery(label="Generated variations")
+output.style(grid=2, height="")
+
+description = \
+"""
+<p style='text-align: center;'>This demo is running on CPU. Working version fixed by Sylvain <a href='https://twitter.com/fffiloni' target='_blank'>@fffiloni</a>. You'll get n pairs of images variations. <br /> 
+Asking for pairs of images instead of more than 2 images in a row helps us to avoid heavy CPU load and connection error out ;)<br />
+Waiting time (for 2 pairs): ~5/10 minutes • NSFW filters enabled • <img id='visitor-badge' alt='visitor badge' src='https://visitor-badge.glitch.me/badge?page_id=gradio-blocks.sd-img-variations' style='display: inline-block' /><br />
+Generate variations on an input image using a fine-tuned version of Stable Diffusion.<br />
+Trained by <a href='https://www.justinpinkney.com' target='_blank'>Justin Pinkney</a> (<a href='https://twitter.com/Buntworthy' target='_blank'>@Buntworthy</a>) at <a href='https://lambdalabs.com/' target='_blank'>Lambda</a><br />
+This version has been ported to 🤗 Diffusers library, see more details on how to use this version in the <a href='https://github.com/LambdaLabsML/lambda-diffusers' target='_blank'>Lambda Diffusers repo</a>.<br />
+For the original training code see <a href='https://github.com/justinpinkney/stable-diffusion' target='_blank'>this repo</a>.
+<img src='https://raw.githubusercontent.com/justinpinkney/stable-diffusion/main/assets/im-vars-thin.jpg' style='display: inline-block;' />
+</p>
+"""
+
+article = \
+"""
+—
+## How does this work?
+The normal Stable Diffusion model is trained to be conditioned on text input. This version has had the original text encoder (from CLIP) removed, and replaced with
+the CLIP _image_ encoder instead. So instead of generating images based a text input, images are generated to match CLIP's embedding of the image.
+This creates images which have the same rough style and content, but different details, in particular the composition is generally quite different.
+This is a totally different approach to the img2img script of the original Stable Diffusion and gives very different results.
+The model was fine tuned on the [LAION aethetics v2 6+ dataset](https://laion.ai/blog/laion-aesthetics/) to accept the new conditioning.
+Training was done on 4xA6000 GPUs on [Lambda GPU Cloud](https://lambdalabs.com/service/gpu-cloud).
+More details on the method and training will come in a future blog post.
+"""
+
+demo = gr.Interface(
+    fn=main,
+    title="Stable Diffusion Image Variations",
+    inputs=inputs,
+    outputs=output,
+    description=description,
+    article=article
+    )
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+torch
+transformers
+scipy
+ftfy
+git+https://github.com/LambdaLabsML/lambda-diffusers.git#egg=lambda-diffusers