Rename functions

Upload 5 files

Upload 4 files

app_v2v.py

Set this space to GPU config to make it work

app.py

Warning

gr.Markdown('# Framepack F1 with Image Input or with Video Input (Video Extension)')

gr.Markdown('# Framepack F1 with Image Input or with Video Input (Video Extension)')

app_v2v.py

No args

Complete imports

app.py

Improve seed

Randomize seed

return min(total_second_length_debug_value * 60 * 2, 600)

Like original

Init

app_v2v.py

Comment logs

Upload 5 files

Upload 4 files

Array of prompts

app.py

13

Good condition

Upload 5 files

triton==3.3.0

torchvision==0.22.0

Upload 4 files

Earlier

Before loop

if len(prompt_parameters) > 1:

[llama_vec, clip_l_pooler, llama_vec_n, clip_l_pooler_n, llama_attention_mask, llama_attention_mask_n] = prompt_parameters.pop(0)

for prompt_part in prompt.split(";"):

Use TeaCache

Use TeaCache

Revert

[llama_vec, clip_l_pooler, llama_vec_n, clip_l_pooler_n, llama_attention_mask, llama_attention_mask_n] = [llama_vec_part, clip_l_pooler_part, llama_vec_n_part, clip_l_pooler_n_part, llama_attention_mask_part, llama_attention_mask_n_part]

[llama_vec, clip_l_pooler, llama_vec_n, clip_l_pooler_n, llama_attention_mask, llama_attention_mask_n] = encode_prompt(prompt_part, n_prompt)

for prompt_part in prompt.split(";"):

[llama_vec, clip_l_pooler, llama_vec_n, clip_l_pooler_n, llama_attention_mask, llama_attention_mask_n] = prompt_parameters.pop(0)

13, # latent_window_size

for prompt_part in prompt.split(";"):

app_file: app.py

Upload 5 files

No more used

Upload 4 files

Move call

Use encode_prompt()