Issues
- 6
error: I put the cursor on 15s of video to generate, the video created is only 5s ! (gradio demo, 768p)
#183 opened by Giribot - 2
Colab notebook?
#188 opened by sdes21 - 2
About finetune miniflux768
#182 opened by lovejing0306 - 0
Is the image to video prompt working?
#190 opened by cocktailpeanut - 2
(not found) option or settings to generate 10s videos with the 768p model with gradio.
#187 opened by Giribot - 3
- 1
- 6
You mentioned releasing the 768p video checkpoint in a few days. Do you have a specific date or timeline for this release
#168 opened by SAT431 - 3
What is the 1024p image checkpoint? Is it a text-to-image model, or is it an image-to-video model?
#141 opened by SAT431 - 4
config.json not found in 'D:\\Data\\Packages\\Pyramid-Flow\\pyramid_flow_model\\diffusion_transformer_768p' (but it's work in 384p)
#146 opened by Giribot - 1
- 1
- 1
- 0
- 1
Black video
#179 opened by jamesstothard - 1
- 3
`extract_vae_latent.sh` CUDA out of memory
#167 opened by JWargrave - 4
Why does the image become increasingly blurry from the second
#178 opened by gameandwhk111111111111111111 - 3
flux 768p result
#177 opened by yjhong89 - 3
is there any quick implement for video to video task based on Pyramid-Flow? for example video editing
#171 opened by huiyan1804 - 6
- 1
Is diffusion_tranformer_image for what ?
#176 opened by yjhong89 - 5
miniflux768
#173 opened by wx331406 - 1
[ERROR] Model initialization failed: The pyramid_flux does not support high resolution now, we will release it after finishing training. You can modify the model_name to pyramid_mmdit to support 768p version generation
#174 opened by Giribot - 1
- 2
- 4
Image generated video can only be selected at 384p
#172 opened by wx331406 - 4
Where can I get LPIPS vgg checkpoints?
#163 opened by vanche - 2
- 6
- 1
- 2
DiT Finetuning
#166 opened by zjq-Jackson - 2
Training issues
#159 opened by rob-hen - 1
- 3
Question on Memory Optimization in PR #75
#150 opened by wladradchenko - 2
Can this model produce infinitely long videos?
#155 opened by xizaoqu - 5
RuntimeError with the new flux models
#158 opened by VigneshSrinivasan10 - 2
Data processing
#157 opened by zjq-Jackson - 1
Qustion about implement of eq. 15 in the Paper.
#151 opened by Binyr - 1
- 7
Questions about implementation
#148 opened by yjhong89 - 1
Install error: ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (thinc)
#154 opened by kinglunalilo - 1
How much VRAM is required to run it without CPU offloading? Specifically, will it work on an RTX 3060 with 12GB of VRAM without relying on the CPU?
#152 opened by SAT431 - 1
Lora finetuning
#153 opened by cseti007 - 2
Creative upscale use-case
#149 opened by cyrildiagne - 4
- 3
what is difference between pyramid_flow_miniflux_bf16_v1.safetensors and pyramid_flow_miniflux_bf16_v2.safetensors ?
#145 opened by ptits - 4
miniflux版本 人像后面还是会崩掉 不知道768的video模型是否会改善。
#144 opened by aigcchumen - 2
Error during text-to-video generation: Torch not compiled with CUDA enabled
#143 opened by axiomgraph - 1
some problem about flux
#140 opened by zzk88862