ReShot — copy the shot, not the actors. Video → depth map, OpenPose skeleton or canny lines for Seedance 2.0/2.5 reference video, MiniMax H3 Fun ControlNet and Wan VACE. Apache-2.0. Open-sourced by Maosika 猫斯卡 (www.maosika.com), the AI short-drama production system.
Python ai-short-dramaai-videocannycomfyuicontrolnetdepth-anythingdepth-estimationdwposemaosikaminimaxopenposepose-controlnetpose-estimationseedanceshort-dramavideo-generationvideo-to-videowan
docs: MiniMax H3 verification of skeleton reference videos — three demo takes re-made with pose as <Video 1>, prompts with seeds, comparison image
wangfeng52987fd9ebe1
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex a52ecde..723cea9 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -23,6 +23,9 @@- Colab notebook and `docs/AGENT_INSTALL.md` cover the new types.- Pose and canny are read at the output size (no "model resolution"), with their own, muchsmaller host-RAM estimate.+- Verified on MiniMax H3: the three demo takes re-made with the skeleton as `<Video 1>` (same+ prompts and sheets) reproduce the six beats like the depth takes; prompts + seeds in+ `docs/prompts/*_pose.txt`, comparison in `docs/img/pose_vs_depth_takes.jpg`.## 0.4.1 — 2026-09-14- **Colab notebook.** `examples/reshot_colab.ipynb` — a free GPU, upload a clip, downloaddiff --git a/README.md b/README.mdindex a9b0cae..f379375 100644--- a/README.md+++ b/README.md@@ -134,7 +134,12 @@ Left to right: [Jiang Xue](docs/prompts/take1_jiangxue_armor.txt) in bronze armo**Doesn't:** faces (use a character sheet), clothes, lighting, colour, props in detail, and anything smaller than a hand. Those come from your prompt and your reference images.-**Depth or pose?** Depth carries the whole picture — where the walls are, who is bigger, a pipe being torn off — and works on anything, people or not. Pose carries only the people, but every limb and finger exactly, and nothing of their body shape or the set. Use pose for dance and martial arts, depth for everything else; when in doubt make both (`--control depth,pose`) and see which one the model follows better. One case where pose is the wrong tool: a tight close-up. The estimator still guesses where the shoulders and hips are when they are off screen, and draws them along the frame edge — depth carries a close-up faithfully. Canny carries the outline of clothes and faces too, so "copy the shot, not the actors" is only half true for it.+**Depth or pose?** Depth carries the whole picture — where the walls are, who is bigger, a pipe being torn off — and works on anything, people or not. Pose carries only the people, but every limb and finger exactly, and nothing of their body shape or the set. Use pose for dance and martial arts, depth for everything else; when in doubt make both (`--control depth,pose`) and see which one the model follows better.++We tested that on MiniMax H3 with the three demo takes: same prompts, same character sheets, only `<Video 1>` swapped from the depth map to the skeleton video (and the two sentences that describe it). All three skeleton takes reproduce the six beats — close-up, brawl, the throw, the panel, the walk out past the fallen guards — at the same level as the depth takes; the throw reads more clearly from the skeleton. One take per condition, different seeds, so read it as "pose works as a reference video too", not as "pose is better". The prompts with seeds are in [`docs/prompts/`](docs/prompts/) (`*_pose.txt`).++<p align="center"><img src="docs/img/pose_vs_depth_takes.jpg" width="864" alt="reference row, then depth take and skeleton take for each of the three characters, six shots each"></p>+<p align="center"><sub>Top: the reference. Then, per character, the take made from the depth map and the take made from the skeleton — six shots each.</sub></p> One case where pose is the wrong tool: a tight close-up. The estimator still guesses where the shoulders and hips are when they are off screen, and draws them along the frame edge — depth carries a close-up faithfully. Canny carries the outline of clothes and faces too, so "copy the shot, not the actors" is only half true for it.Things we learned making the demo:diff --git a/README.zh-CN.md b/README.zh-CN.mdindex fc53ae2..1f9d978 100644--- a/README.zh-CN.md+++ b/README.zh-CN.md@@ -134,7 +134,12 @@ is transferred onto <Subject 1> and <Subject 2>; its grey depth look is not tran**不能:** 脸(用定妆图)、衣服、光线、颜色、道具细节,以及比手还小的东西。这些全靠你的提示词和参考图。-**深度图还是骨架?** 深度图带走整个画面——墙在哪、谁更大、一根管子被扯下来——人和非人都管用。骨架只带人,但每根肢体每根手指都准,体型和场景一点不带。跳舞、武打选骨架,其余选深度图;拿不准就两个都出(`--control depth,pose`),看模型跟哪个跟得更好。有一种情况骨架不合适:大特写。肩和髋不在画面里时估计器照样会猜,把它们画在画面边上——特写老老实实用深度图。线稿会把服装和脸的轮廓也带过去,「只复制走位」对它只成立一半。+**深度图还是骨架?** 深度图带走整个画面——墙在哪、谁更大、一根管子被扯下来——人和非人都管用。骨架只带人,但每根肢体每根手指都准,体型和场景一点不带。跳舞、武打选骨架,其余选深度图;拿不准就两个都出(`--control depth,pose`),看模型跟哪个跟得更好。++我们在 MiniMax H3 上用演示的三段片做了实测:提示词、定妆图完全一样,只把 `<Video 1>` 从深度图换成骨架视频(连带改了描述它的两句话)。三条骨架版都复现了六个节拍——特写、群殴、过肩摔、撞控制台、跨过倒地守卫走出门——和深度版一个水平,过肩摔那一镜骨架版更清楚。每种条件只出了一条、seed 不同,所以只能读成「骨架当参考视频也行」,不能读成「骨架更好」。带 seed 的提示词在 [`docs/prompts/`](docs/prompts/)(`*_pose.txt`)。++<p align="center"><img src="docs/img/pose_vs_depth_takes.jpg" width="864" alt="第一行参考片;之后每个角色两行:深度版成片和骨架版成片,各六镜"></p>+<p align="center"><sub>最上面是参考片。往下每个角色两行:用深度图出的片、用骨架出的片,各六个镜头。</sub></p>有一种情况骨架不合适:大特写。肩和髋不在画面里时估计器照样会猜,把它们画在画面边上——特写老老实实用深度图。线稿会把服装和脸的轮廓也带过去,「只复制走位」对它只成立一半。做演示时踩出来的几条:diff --git a/docs/img/pose_vs_depth_takes.jpg b/docs/img/pose_vs_depth_takes.jpgnew file mode 100644index 0000000..196d55aBinary files /dev/null and b/docs/img/pose_vs_depth_takes.jpg differdiff --git a/docs/prompts/take1_jiangxue_armor_pose.txt b/docs/prompts/take1_jiangxue_armor_pose.txtnew file mode 100644index 0000000..81c5586--- /dev/null+++ b/docs/prompts/take1_jiangxue_armor_pose.txt@@ -0,0 +1,27 @@+# MiniMax H3, <Video 1> = the OpenPose skeleton video (reshot --control pose --target h3, scaled to 320x176), seed 1093962678, 12 s 16:9 720p, 340 s on one H3 machine (2026-09-14).+# Identical to the depth-map take except the two sentences that define <Video 1> and say its look is not to be copied.++subject_definitions:+<Subject 1> is the young woman shown in <Picture 1> and in close-up in <Picture 2>, Jiang Xue, a warrior with a high ponytail, red flame tattoos across her chest and shoulders and a dark leather-and-bronze armored corset; both pictures are used only for her appearance and her face must match <Picture 2> exactly.+<Subject 2> is a group of four guards in plain black tactical clothing without any markings, one of them holding a steel baton, the largest of them a head taller than the others.+<Subject 3> is the fight choreography and camera movement shown in <Video 1>, an OpenPose skeleton video — coloured stick figures on black, one per person: one fighter leans on a corridor wall in close-up, kicks off it to tear down a pipe, fights several men, is grabbed from behind by the largest and throws him, slams the last one into a wall panel, wipes the mouth in close-up, then walks away through a door past the fallen men.+<Subject 4> is a narrow steel corridor with riveted grey walls, flickering ceiling strip lights, a blinking red alarm lamp, sprinkler mist hanging in the air, stacked metal crates along one side, a wall control panel and a heavy sliding door at the far end.+summary:+[reference generation] <Subject 1> fights <Subject 2> inside <Subject 4>, reproducing shot for shot the choreography and camera of <Subject 3>: a close-up with eyes closed, kicking off the wall to tear down a pipe, a brawl in which she throws the largest guard over her shoulder, slamming the last guard into the control panel, wiping her mouth, and walking out through the door.+retention_analysis:+<Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3], [Shot 4], [Shot 5], [Shot 6]): fully_preserved - her face, ponytail, chest tattoos and armored corset are retained exactly as in <Picture 1>.+<Subject 2> (appears in [Shot 3], [Shot 4], [Shot 6]): fully_preserved - plain black-clad guards.+<Subject 3> (appears in [Shot 1], [Shot 2], [Shot 3], [Shot 4], [Shot 5], [Shot 6]): attribute_transfer - every action, position, timing and camera move of <Video 1> is transferred onto <Subject 1> and <Subject 2>; the stick-figure look is not transferred.+<Subject 4> (appears in all shots): fully_preserved - the corridor, crates, panel and door layout are retained.+detailed_description:+The target video is a photorealistic action fantasy with cold cinematic corridor lighting and a teal-and-red color grade.+[Shot 1] A tight close-up frames the face of <Subject 1> leaning back against the corridor wall of <Subject 4>, eyes closed, jaw set; the flickering light plays across her face, then her eyes snap open and she lets out a short shout as the camera holds a static shot.+[Shot 2] At 00:01.000, the shot cuts to a low medium-wide shot as <Subject 1> kicks off the wall, springs up, and rips a steel pipe from the wall fixture in a burst of sparks; the camera tracks her with small amplitude at fast speed.+[Shot 3] At 00:02.000, the camera cuts to a handheld medium shot inside the brawl in <Subject 4>: <Subject 1> drives the pipe into the ribs of one guard of <Subject 2>, hooks his neck and spins him into the wall, then leaps into a flying kick that sends a second guard crashing into the crates. The largest guard charges in and wraps <Subject 1> from behind in a crushing bear hug; <Subject 1> snaps her head back into his face, twists, and throws him over her shoulder so that his body slams flat onto the floor. The camera shakes slightly and trucks right to follow the action.+[Shot 4] At 00:07.000, the shot cuts to a medium shot as <Subject 1> grabs the last guard of <Subject 2> by the collar, drags him to the control panel and smashes his head into it; sparks spray from the panel and the heavy door at the end of <Subject 4> hisses open. The camera pushes in with small amplitude.+[Shot 5] At 00:08.500, the camera cuts to a close-up of <Subject 1>, chest heaving, wiping blood from the corner of her mouth with the back of her hand and staring past the camera; the camera holds a static shot.+[Shot 6] At 00:10.000, the shot cuts to a wide shot from low behind the fallen guards of <Subject 2> on the corridor floor as <Subject 1> steps over them and walks away through the open door into darkness; the camera holds a static shot.+overall_soundscape:+Low electrical hum of the corridor, dripping sprinkler water, heavy body impacts, the clang of the pipe on metal, sparks crackling, ragged breathing, the hiss of the hydraulic door.+non_diegetic_music:+A sparse, low pulsing synth bass with a slow heartbeat-like kick that fades out at the end.diff --git a/docs/prompts/take2_suwan_qipao_pose.txt b/docs/prompts/take2_suwan_qipao_pose.txtnew file mode 100644index 0000000..56512cd--- /dev/null+++ b/docs/prompts/take2_suwan_qipao_pose.txt@@ -0,0 +1,27 @@+# MiniMax H3, <Video 1> = the OpenPose skeleton video (reshot --control pose --target h3, scaled to 320x176), seed 1488156354, 12 s 16:9 720p, 340 s on one H3 machine (2026-09-14).+# Identical to the depth-map take except the two sentences that define <Video 1> and say its look is not to be copied.++subject_definitions:+<Subject 1> is the young woman shown in <Picture 1> and in close-up in <Picture 2>, Su Wan, an elegant beauty with black hair in a low side bun, a pearl earring and a dark green velvet qipao; both pictures are used only for her appearance and her face must match <Picture 2> exactly.+<Subject 2> is a group of four guards in plain black tactical clothing without any markings, one of them holding a steel baton, the largest of them a head taller than the others.+<Subject 3> is the fight choreography and camera movement shown in <Video 1>, an OpenPose skeleton video — coloured stick figures on black, one per person: one fighter leans on a corridor wall in close-up, kicks off it to tear down a pipe, fights several men, is grabbed from behind by the largest and throws him, slams the last one into a wall panel, wipes the mouth in close-up, then walks away through a door past the fallen men.+<Subject 4> is a narrow steel corridor with riveted grey walls, flickering ceiling strip lights, a blinking red alarm lamp, sprinkler mist hanging in the air, stacked metal crates along one side, a wall control panel and a heavy sliding door at the far end.+summary:+[reference generation] <Subject 1> fights <Subject 2> inside <Subject 4>, reproducing shot for shot the choreography and camera of <Subject 3>: a close-up with eyes closed, kicking off the wall to tear down a pipe, a brawl in which she throws the largest guard over her shoulder, slamming the last guard into the control panel, wiping her mouth, and walking out through the door.+retention_analysis:+<Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3], [Shot 4], [Shot 5], [Shot 6]): fully_preserved - her face, side bun, pearl earring and green velvet qipao are retained exactly as in <Picture 1>.+<Subject 2> (appears in [Shot 3], [Shot 4], [Shot 6]): fully_preserved - plain black-clad guards.+<Subject 3> (appears in [Shot 1], [Shot 2], [Shot 3], [Shot 4], [Shot 5], [Shot 6]): attribute_transfer - every action, position, timing and camera move of <Video 1> is transferred onto <Subject 1> and <Subject 2>; the stick-figure look is not transferred.+<Subject 4> (appears in all shots): fully_preserved - the corridor, crates, panel and door layout are retained.+detailed_description:+The target video is a photorealistic action fantasy with cold cinematic corridor lighting and a teal-and-red color grade.+[Shot 1] A tight close-up frames the face of <Subject 1> leaning back against the corridor wall of <Subject 4>, eyes closed, jaw set; the flickering light plays across her face, then her eyes snap open and she lets out a short shout as the camera holds a static shot.+[Shot 2] At 00:01.000, the shot cuts to a low medium-wide shot as <Subject 1> kicks off the wall, springs up, and rips a steel pipe from the wall fixture in a burst of sparks; the camera tracks her with small amplitude at fast speed.+[Shot 3] At 00:02.000, the camera cuts to a handheld medium shot inside the brawl in <Subject 4>: <Subject 1> drives the pipe into the ribs of one guard of <Subject 2>, hooks his neck and spins him into the wall, then leaps into a flying kick that sends a second guard crashing into the crates. The largest guard charges in and wraps <Subject 1> from behind in a crushing bear hug; <Subject 1> snaps her head back into his face, twists, and throws him over her shoulder so that his body slams flat onto the floor. The camera shakes slightly and trucks right to follow the action.+[Shot 4] At 00:07.000, the shot cuts to a medium shot as <Subject 1> grabs the last guard of <Subject 2> by the collar, drags him to the control panel and smashes his head into it; sparks spray from the panel and the heavy door at the end of <Subject 4> hisses open. The camera pushes in with small amplitude.+[Shot 5] At 00:08.500, the camera cuts to a close-up of <Subject 1>, chest heaving, wiping blood from the corner of her mouth with the back of her hand and staring past the camera; the camera holds a static shot.+[Shot 6] At 00:10.000, the shot cuts to a wide shot from low behind the fallen guards of <Subject 2> on the corridor floor as <Subject 1> steps over them and walks away through the open door into darkness; the camera holds a static shot.+overall_soundscape:+Low electrical hum of the corridor, dripping sprinkler water, heavy body impacts, the clang of the pipe on metal, sparks crackling, ragged breathing, the hiss of the hydraulic door.+non_diegetic_music:+A sparse, low pulsing synth bass with a slow heartbeat-like kick that fades out at the end.diff --git a/docs/prompts/take3_rabbit_boxer_pose.txt b/docs/prompts/take3_rabbit_boxer_pose.txtnew file mode 100644index 0000000..2c28e60--- /dev/null+++ b/docs/prompts/take3_rabbit_boxer_pose.txt@@ -0,0 +1,27 @@+# MiniMax H3, <Video 1> = the OpenPose skeleton video (reshot --control pose --target h3, scaled to 320x176), seed 927905444, 12 s 16:9 720p, 328 s on one H3 machine (2026-09-14).+# Identical to the depth-map take except the two sentences that define <Video 1> and say its look is not to be copied.++subject_definitions:+<Subject 1> is the anthropomorphic rabbit shown in <Picture 1>, a female rabbit with cream-tan fur, dark-tipped upright ears, big green eyes, a tiny silver ear stud, a grey hoodie, black shorts and white hand wraps, standing upright like a person, about 1.5 meters tall (baseline 1x), her head reaching the wolf's shoulder; the picture (face on the left, full body on the right) is used only for her appearance and her face, fur color and outfit must match it exactly. She is the only rabbit in the entire film: there is exactly one rabbit, and every other character is a predator of <Subject 2>.+<Subject 2> is a group of three anthropomorphic predators standing upright like people: a grey wolf about 1.9 meters tall, an orange tiger about 2.0 meters tall and a brown bear about 2.1 meters tall (about 1.3x the rabbit, never more than 1.5x), all in plain black leather jackets without any markings, one of them holding a steel bar; none of them is a rabbit and none of them has long ears.+<Subject 3> is the fight choreography and camera movement shown in <Video 1>, an OpenPose skeleton video — coloured stick figures on black, one per person: one fighter leans on a corridor wall in close-up, kicks off it to tear down a pipe, fights several opponents, is grabbed from behind by the largest and throws him, slams the last one into a wall panel, wipes the mouth in close-up, then walks away through a door past the fallen opponents.+<Subject 4> is a narrow steel corridor with riveted grey walls, flickering ceiling strip lights, a blinking red alarm lamp, sprinkler mist in the air, stacked metal crates along one side, a wall control panel with round colored buttons and a heavy sliding door at the far end; no text, letters or signs anywhere.+summary:+[reference generation] <Subject 1> fights <Subject 2> inside <Subject 4>, reproducing shot for shot the choreography and camera of <Subject 3>: a close-up with eyes closed, kicking off the wall to tear down a pipe, a brawl in which she throws the bear over her shoulder, slamming the last predator into the control panel, wiping her mouth, and walking out through the door. The whole film is a cartoon: no blood, no text anywhere, and exactly one rabbit on screen at any time.+retention_analysis:+<Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3], [Shot 4], [Shot 5], [Shot 6]): fully_preserved - her cream-tan fur, green eyes, ear stud, grey hoodie and hand wraps are retained exactly as in <Picture 1>; she appears once per shot, never duplicated.+<Subject 2> (appears in [Shot 3], [Shot 4], [Shot 6]): fully_preserved - wolf, tiger and bear in plain black jackets.+<Subject 3> (appears in [Shot 1], [Shot 2], [Shot 3], [Shot 4], [Shot 5], [Shot 6]): attribute_transfer - every action, position, timing and camera move of <Video 1> is transferred onto <Subject 1> and <Subject 2>; the stick-figure look is not transferred.+<Subject 4> (appears in all shots): fully_preserved - the corridor, crates, panel and door layout are retained.+detailed_description:+The target video is a cinematic 3D feature animation with cute stylized animal characters, soft fluffy fur, soft key light with bounce fill, and volumetric light.+[Shot 1] A tight close-up frames the face of <Subject 1> leaning back against the corridor wall of <Subject 4>, eyes closed, ears flat; the flickering light plays across her fur, then her big eyes snap open and she lets out a short shout as the camera holds a static shot.+[Shot 2] At 00:01.000, the shot cuts to a low medium-wide shot as <Subject 1> kicks off the wall, springs up, and rips a steel pipe from the wall fixture in a burst of sparks; the camera tracks her with small amplitude at fast speed.+[Shot 3] At 00:02.000, the camera cuts to a handheld medium shot inside the brawl in <Subject 4>: <Subject 1> drives the pipe into the ribs of the wolf of <Subject 2>, hooks his neck and spins him into the wall, then leaps into a flying kick that sends the tiger crashing into the crates. The bear charges in and wraps <Subject 1> from behind in a crushing bear hug; she snaps her head back into his snout, twists, and throws him over her shoulder so that his huge body slams flat onto the floor. The camera shakes slightly and trucks right to follow the action.+[Shot 4] At 00:07.000, the shot cuts to a medium shot as <Subject 1> grabs the wolf of <Subject 2> by the collar, drags him to the control panel and bonks his head into it; sparks spray from the panel and the heavy door at the end of <Subject 4> hisses open. The camera pushes in with small amplitude.+[Shot 5] At 00:08.500, the camera cuts to a close-up of <Subject 1>, chest heaving, wiping her mouth with the back of her paw and staring past the camera; the camera holds a static shot.+[Shot 6] At 00:10.000, the shot cuts to a wide shot from low behind the fallen wolf, tiger and bear of <Subject 2> lying on the corridor floor as <Subject 1>, the rabbit with her long upright ears clearly visible from behind, steps over them and walks away alone through the open door into the light; none of the predators stands up; the camera holds a static shot.+overall_soundscape:+Low electrical hum, dripping sprinkler water, soft cartoon body impacts, the clang of the pipe on metal, sparks crackling, quick breathing, the hiss of the door.+non_diegetic_music:+A playful but driving orchestral action cue with brass hits on the impacts, fading to a soft heartbeat at the end.