From 1e6d1bbb8233cfe683b2cae73fa97f55eb40bab7 Mon Sep 17 00:00:00 2001 From: DefTruth <31974251+DefTruth@users.noreply.github.com> Date: Thu, 7 Nov 2024 02:40:13 +0000 Subject: [PATCH 1/3] fix parallel rand device --- tools/parallel_inference/parallel_inference_xdit.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/parallel_inference/parallel_inference_xdit.py b/tools/parallel_inference/parallel_inference_xdit.py index 03bc268..d0b8029 100644 --- a/tools/parallel_inference/parallel_inference_xdit.py +++ b/tools/parallel_inference/parallel_inference_xdit.py @@ -78,8 +78,9 @@ def main(): num_frames=input_config.num_frames, prompt=input_config.prompt, num_inference_steps=input_config.num_inference_steps, - generator=torch.Generator(device="cuda").manual_seed(input_config.seed), + generator=torch.Generator().manual_seed(input_config.seed), guidance_scale=6, + use_dynamic_cfg=True, ).frames[0] end_time = time.time() From abe334f196b8c64f0ab24fa30a56b140647881c3 Mon Sep 17 00:00:00 2001 From: zR <2448370773@qq.com> Date: Fri, 8 Nov 2024 12:44:54 +0800 Subject: [PATCH 2/3] Update test.txt --- sat/configs/test.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sat/configs/test.txt b/sat/configs/test.txt index 8d035c0..94ad730 100644 --- a/sat/configs/test.txt +++ b/sat/configs/test.txt @@ -1,4 +1,4 @@ In the haunting backdrop of a warIn the haunting backdrop of a war-torn city, where ruins and crumbled walls tell a story of devastation, a poignant close-up frames a young girl. Her face is smudged with ash, a silent testament to the chaos around her. Her eyes glistening with a mix of sorrow and resilience, capturing the raw emotion of a world that has lost its innocence to the ravages of conflict. The camera follows behind a white vintage SUV with a black roof rack as it speeds up a steep dirt road surrounded by pine trees on a steep mountain slope, dust kicks up from its tires, the sunlight shines on the SUV as it speeds along the dirt road, casting a warm glow over the scene. The dirt road curves gently into the distance, with no other cars or vehicles in sight. The trees on either side of the road are redwoods, with patches of greenery scattered throughout. The car is seen from the rear following the curve with ease, making it seem as if it is on a rugged drive through the rugged terrain. The dirt road itself is surrounded by steep hills and mountains, with a clear blue sky above with wispy clouds. A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting. -A street artist, clad in a worn-out denim jacket and a colorful bandana, stands before a vast concrete wall in the heart, holding a can of spray paint, spray-painting a colorful bird on a mottled wall.-torn city, where ruins and crumbled walls tell a story of devastation, a poignant close-up frames a young girl. Her face is smudged with ash, a silent testament to the chaos around her. Her eyes glistening with a mix of sorrow and resilience, capturing the raw emotion of a world that has lost its innocence to the ravages of conflict. \ No newline at end of file +A street artist, clad in a worn-out denim jacket and a colorful banana, stands before a vast concrete wall in the heart, holding a can of spray paint, spray-painting a colorful bird on a mottled wall.-torn city, where ruins and crumbled walls tell a story of devastation, a poignant close-up frames a young girl. Her face is smudged with ash, a silent testament to the chaos around her. Her eyes glistening with a mix of sorrow and resilience, capturing the raw emotion of a world that has lost its innocence to the ravages of conflict. \ No newline at end of file From cd5ceca22b3b16e0a8dee8bf902236a852e198e2 Mon Sep 17 00:00:00 2001 From: zR <2448370773@qq.com> Date: Tue, 12 Nov 2024 00:41:23 +0800 Subject: [PATCH 3/3] fix resolution docs --- README.md | 2 +- README_ja.md | 2 +- README_zh.md | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 9f8122e..90839de 100644 --- a/README.md +++ b/README.md @@ -188,7 +188,7 @@ models we currently offer, along with their foundational information. Video Resolution 1360 * 768 - 256 <= W <=1360
256 <= H <=768
W,H % 16 == 0 + Min(W, H) = 768
768 ≤ Max(W, H) ≤ 1360
Max(W, H) % 16 = 0 720 * 480 diff --git a/README_ja.md b/README_ja.md index 9962d1b..8430fb6 100644 --- a/README_ja.md +++ b/README_ja.md @@ -180,7 +180,7 @@ CogVideoXは、[清影](https://chatglm.cn/video?fr=osm_cogvideox) と同源の ビデオ解像度 1360 * 768 - 256 <= W <=1360
256 <= H <=768
W,H % 16 == 0 + Min(W, H) = 768
768 ≤ Max(W, H) ≤ 1360
Max(W, H) % 16 = 0 720 * 480 diff --git a/README_zh.md b/README_zh.md index c66fc85..73636e9 100644 --- a/README_zh.md +++ b/README_zh.md @@ -171,7 +171,7 @@ CogVideoX是 [清影](https://chatglm.cn/video?fr=osm_cogvideox) 同源的开源 视频分辨率 1360 * 768 - 256 <= W <=1360
256 <= H <=768
W,H % 16 == 0 + Min(W, H) = 768
768 ≤ Max(W, H) ≤ 1360
Max(W, H) % 16 = 0 720 * 480