Skip to content

issues Search Results · repo:damian0815/compel language:"Jupyter Notebook"

Filter by

0 results
 (65 ms)

0 results

indamian0815/compel (press backspace or delete to remove)

damian0815/compel
Support SD3.5 large

Hello I tried to use compel with SD3.5-large but got this error: prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0) RuntimeError: Sizes of tensors must match except in dimension ...
  • gebaltso
  • 2
  • Opened 
    on Oct 31, 2024
  • #107

damian0815/compel
Support PhotoMaker

Trying to use compel on the photomaker pipeline. Got error: RuntimeError: CUDA error: device-side assert triggered pipe = PhotoMakerStableDiffusionXLPipeline.from_single_file( model.safetensors ...
  • kelvincai522
  • 2
  • Opened 
    on Oct 22, 2024
  • #106

damian0815/compel
TypeError: unsupported operand type(s) for +: 'NoneType' and 'int' in get_embeddings_for_weighted_prompt_fragments

Hi @damian0815 , I found a case that makes compel crash, here is a MRE (I did not attempt to find the shortest possible prompt that makes it crash): using compel==2.0.3 pipe = StableDiffusionXLPipeline.from_pretrained( ...
  • Clement-Lelievre
  • Opened 
    on Sep 27, 2024
  • #105

damian0815/compel
Multiple unclosed brackets slow down/crash Prompt Parser

This snipped slows it down a lot, and sometimes crashes with too many recursive calls error. from compel import PromptParser parser = PromptParser() for i in range(1, 100): print(f Testing {i}... ...
  • sssemil
  • Opened 
    on Sep 3, 2024
  • #103

damian0815/compel
Paralism in generating embeddings

Hi, I was looking over the docs, and batch inference was mentioned. I looked at the code, and it is not batch inference. It is sequential inference. I was really hoping for batch inference because I ...
  • Daniel-SicSo-Edinburgh
  • 1
  • Opened 
    on Aug 17, 2024
  • #102

damian0815/compel
Question: Do I still need to set negative_prompt to pipe() or I should just combine them to prompts with "-"?

Hi there, thanks for the great work. Just a quick question, should I do: pipe(prompt_embeds=prompt_embeds, negative_prompt=negative_prompt, ...) or just pipe(prompt_embeds=prompt_embeds, ...) while ...
  • tclzcja
  • Opened 
    on Aug 8, 2024
  • #100

damian0815/compel
Support Flux.1

Can Flux.1 be supported ?
  • MohamedAliRashad
  • 6
  • Opened 
    on Aug 4, 2024
  • #99

damian0815/compel
Support for AuraFlow

The current Compel doesnt work for fal/AuraFlow. Any works on supporting it.
  • waadarsh
  • Opened 
    on Jul 31, 2024
  • #98

damian0815/compel
ELLA & Compel

I m curious if Compel is compatible with algorithms for better prompt adherence like Ella, and if not, what do you guys suggest we do to make this stuff work? Obviously, we d like people to set weights ...
  • andupotorac
  • Opened 
    on Jul 30, 2024
  • #97

damian0815/compel
Incorrect pooled embeds

While benchmarking our internal prompt weighting, I noticed that compel s pooled embeddings change with different prompt weighting. I.e. pooled embeds of test != pooled embeds of (test)0.9. Compel tokenizes ...
  • BitPhinix
  • 1
  • Opened 
    on Jul 3, 2024
  • #96
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub