Update diffusers default snippets to be complete. #907
Conversation
Vaibhavs10
requested review from
SBrandeis,
Wauplin,
gary149,
julien-c,
osanseviero and
pcuenca
as code owners
|
🔥 |
|
the failing tests are unrelated to this pr |
|
Will wait for @sayakpaul or @apolinario to approve before merging! Thanks @mishig25 for fixing the lint issues 🐐 |
| pipe = DiffusionPipeline.from_pretrained("${model.id}") | ||
| prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" | ||
| image = pipe(prompt).images[0]`, |
There was a problem hiding this comment.
Nit: as discussed in Slack, having a prompt might be a bit confusing due to many models expecting certain tokens. In any case, this is fine I think to showcase usage
There was a problem hiding this comment.
For LoRA models would it make sense to read the examples from the README? or is that an overkill?
ref: https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-AntiBlur/blob/main/README.md?code=true#L12
|
Well constructed LoRA models have an Otherwise lgtm |
|
Will follow up w/ showing Gallery prompts in a subsequent PR. Thanks for the reviews everyone! |
Addressing comments left on #907, specially for LoRAs
Addressing comments left on #907, specially for LoRAs --------- Co-authored-by: multimodalart <[email protected]> Co-authored-by: Mishig <[email protected]> Co-authored-by: vb <[email protected]>
Slack chat for ref: https://huggingface.slack.com/archives/C04PJ0H35UM/p1726563327331199?thread_ts=1725899853.249099&cid=C04PJ0H35UM