# Img2Img keeps devolving into psychedelics

**URL:** <https://discuss.huggingface.co/t/img2img-keeps-devolving-into-psychedelics/23739>\
**Category:** Beginners\
**Created:** [September 28, 2022, 5:32pm UTC](https://discuss.huggingface.co/t/img2img-keeps-devolving-into-psychedelics/23739 "2022-09-28T17:32:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rhenretta](https://avatars.discourse-cdn.com/v4/letter/r/d6d6ee/32.png) [@rhenretta](https://discuss.huggingface.co/u/rhenretta)\
**Post date:** [September 28, 2022, 5:32pm UTC](https://discuss.huggingface.co/t/img2img-keeps-devolving-into-psychedelics/23739/1 "2022-09-28T17:32:21Z")

</div>

I’m trying to use StableDiffusionPipeline to create a first image from a prompt, and then turn it into a video by running StableDiffusionImg2ImgPipeline for 200 frames. The StableDiffusionPipeline image is fine, but no matter what settings I use, the Img2Img pipeline always devolves into craziness.

I’ve tried many different strengths and inference steps, but they all end up the same. For some reason, usually very high in purple. Here is an example:

> **[An AI made this video - StableDiffusion art #2](https://www.youtube.com/shorts/Uc9HjtQpUuY)**
>
> I'm trying to find a way to prevent significant changes between images. I'm not a huge fan of weird effect, and working to minimize that, but the way his he...

My current code is

```
torch.cuda.empty_cache()
images = []
log_line(log, 'Generate button clicked')
nsfw = False
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.to('cuda')

with autocast('cuda'):
    data = pipe(prompt, num_inference_steps=inference_steps)
    log_line(log, data)
    image = data.images[0]
    images.append(image)
    if data.nsfw_content_detected[0]:
        st.error("Prompt returned nsfw")
        nsfw = True
    log_line(log, f'Frame 1 returned')

size = (image.size[1], image.size[0])
filename = f'{str(uuid.uuid4())}.mp4'
log_line(log, f'Creating file {filename}')
video = cv.VideoWriter(filename, cv.VideoWriter_fourcc(*'mp4v'), 10, size)
video.write(np.array(data.images[0]))

pipe = StableDiffusionImg2ImgPipeline.from_pretrained(model_id, use_auth_token=token).from_pretrained(model_id, torch_dtype=torch.float16)
pipe.to('cuda')
for n in range(frames-1):
    with autocast("cuda"):
        data = pipe(prompt, init_image=image, num_inference_steps=inference_steps, strength=strength)
        log_line(log, f'Frame {n+2} rendered - steps: {inference_steps}, strength={strength}')
        if data.nsfw_content_detected[0]:  
            log_line(log, f'Frame {n+2} skipped for nsfw')
        else:
            image = data.images[0]
            images.append(image)
            output.empty()
            output.image(images)
            video.write(np.array(image))

video.release()

```